RRepoGEO

REPOGEO REPORT · LITE

ndif-team/nnsight

Default branch main · commit 15af9c55 · scanned 6/3/2026, 11:01:59 AM

GitHub: 946 stars · 91 forks

AI VISIBILITY SCORE
40 /100
Critical
Category recall
0 / 2
Not recommended in any query
Rule findings
2 pass · 0 warn · 0 fail
Objective metadata checks
AI knows your name
3 / 3
Direct prompts that named your repo
HOW TO READ THIS REPORT

Action plan is what to do next — copy-pasteable changes prioritized by impact. Category visibility is the real GEO test: when a user asks an AI a brand-free question that should surface ndif-team/nnsight, does the AI actually recommend you — or your competitors? Objective checks verify the metadata signals AI engines weight first. Self-mention check detects whether AI even knows you exist by name.

Action plan — copy-paste fixes

3 prioritized changes generated by gemini-2.5-flash. Mark items done after you ship the fix.

OVERALL DIRECTION
  • highreadme#1
    Reposition the README H3 to highlight runtime intervention for LLMs

    Why:

    CURRENT
    <h3 align="center">Interpret and manipulate the internals of deep learning models</h3>
    COPY-PASTE FIX
    <h3 align="center">Programmatic runtime intervention and causal manipulation for PyTorch models, especially LLMs</h3>
  • mediumtopics#2
    Add more specific topics to improve categorization

    Why:

    CURRENT
    interpretability, machine-learning, neural-networks, python, pytorch
    COPY-PASTE FIX
    interpretability, machine-learning, neural-networks, python, pytorch, mechanistic-interpretability, llm-interpretability, causal-inference, runtime-intervention
  • mediumcomparison#3
    Add a 'Why nnsight?' section to the README with its core differentiator

    Why:

    COPY-PASTE FIX
    Add the following to your README:
```markdown
## Why nnsight?

Nnsight's core differentiator is its context-manager-based API that enables the declarative, batched, and lazy orchestration of multiple, complex interventions and modifications to model activations within a single forward pass. This significantly simplifies experiment design and execution compared to manual, imperative approaches.
```

Category GEO backends resolved for this scan: google/gemini-2.5-flash, deepseek/deepseek-v4-flash

Category visibility — the real GEO test

Brand-free queries asked to google/gemini-2.5-flash. Did AI recommend you, or someone else?

Same questions for every model — switch tabs to compare answers and rankings.

Recall
0 / 2
0% of queries surface ndif-team/nnsight
Avg rank
—
Lower is better. #1 = top recommendation.
Share of voice
0%
Of all named tools, what % are you?
Top rival
Captum
Recommended in 1 of 2 queries
COMPETITOR LEADERBOARD
  1. Captum · recommended 1×
  2. PyTorch-Ignite · recommended 1×
  3. SHAP · recommended 1×
  4. LRP Toolbox · recommended 1×
  5. Lucid · recommended 1×
  • CATEGORY QUERY
    Python library to inspect and interpret internal states of PyTorch models?
    you: not recommended
    AI recommended (in order):
    1. Captum
    2. PyTorch-Ignite
    3. SHAP
    4. LRP Toolbox
    5. Lucid
    6. DeepExplain
    7. TorchRay

    AI recommended 7 alternatives but never named ndif-team/nnsight. This is the gap to close.

    Show full AI answer
  • CATEGORY QUERY
    What Python tools enable runtime intervention in deep neural network forward passes?
    you: not recommended
    AI recommended (in order):
    1. PyTorch
    2. TensorFlow
    3. Keras Functional API
    4. Keras Subclassing API
    5. tf.data.Dataset.map
    6. Keras (Sequential API)
    7. DeepMind's JAX
    8. jax.debug.print
    9. jax.debug.breakpoint
    10. ONNX Runtime

    AI recommended 10 alternatives but never named ndif-team/nnsight. This is the gap to close.

    Show full AI answer

Objective checks

Rule-based audits of metadata signals AI engines weight most.

  • Metadata completeness
    pass

  • README presence
    pass

Self-mention check

Does AI even know your repo exists when asked about it directly?

  • Compared to common alternatives in this category, what is the core differentiator of ndif-team/nnsight?
    pass
    AI named ndif-team/nnsight explicitly

    AI answers can be confidently wrong. Read for accuracy: does it match your actual tech stack, audience, and differentiator?

  • If a team adopts ndif-team/nnsight in production, what risks or prerequisites should they evaluate first?
    pass
    AI named ndif-team/nnsight explicitly

    AI answers can be confidently wrong. Read for accuracy: does it match your actual tech stack, audience, and differentiator?

  • In one sentence, what problem does the repo ndif-team/nnsight solve, and who is the primary audience?
    pass
    AI named ndif-team/nnsight explicitly

    AI answers can be confidently wrong. Read for accuracy: does it match your actual tech stack, audience, and differentiator?

Embed your GEO score

Drop this badge into the README of ndif-team/nnsight. It auto-updates whenever the report is rescanned and links back to the latest report — easy public proof that you care about AI discoverability.

RepoGEO badge previewLive preview
MARKDOWN (README)
[![RepoGEO](https://repogeo.com/badge/ndif-team/nnsight.svg)](https://repogeo.com/en/r/ndif-team/nnsight)
HTML
<a href="https://repogeo.com/en/r/ndif-team/nnsight"><img src="https://repogeo.com/badge/ndif-team/nnsight.svg" alt="RepoGEO" /></a>
Pro

Subscribe to Pro for deep diagnoses

ndif-team/nnsight — Lite scans stay free; this card itemizes Pro deep limits vs Lite.

  • Deep reports10 / month
  • Brand-free category queries5 vs 2 in Lite
  • Prioritized action items8 vs 3 in Lite
ndif-team/nnsight — RepoGEO report