© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenAI · Weight-Sparse Transformers
    5. CircuitGPT-Python
    7. MLP
    9. 6-MLP
    11. 7736
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    return statement

    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
    Not in Any Lists

    No Comments

    Negative Logits
    loat
    -0.03
    [int
    -0.03
    (int
    -0.02
     del
    -0.02
    int
    -0.02
     int
    -0.02
     float
    -0.02
     np
    -0.02
    resh
    -0.01
    _route
    -0.01
    POSITIVE LOGITS
    .split
    0.05
    split
    0.05
    _string
    0.04
    _str
    0.04
    [str
    0.04
    join
    0.04
     ""
    0.04
     str
    0.03
    .strip
    0.03
    "{
    0.03
    Activations Density 31.443%

    No Known Activations