© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. OpenAI · Weight-Sparse Transformers
    5. CircuitGPT-Python
    7. MLP
    9. 6-MLP
    11. 1492
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    `Counter` or `len` function

    python-code · gemini-2.5-flash-lite

    print function calls (negative activations)

    python-code · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 256 tokens each
    Dataset (Dashboard)
    neuronpedia/python-code-simplified
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     function
    -0.06
    dule
    -0.05
     None
    -0.04
    None
    -0.04
    .values
    -0.04
    py
    -0.03
    .index
    -0.03
    .parent
    -0.03
    erate
    -0.03
     main
    -0.03
    POSITIVE LOGITS
     and
    0.04
    ,
    0.03
     q
    0.02
    .pop
    0.02
    §
    0.02
    ","
    0.02
     {}↵↵
    0.02
    cell
    0.02
    ject
    0.02
    node
    0.02
    Activations Density 99.840%

    No Known Activations