© 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. 3445
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    arguments to function

    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
    igh
    -0.09
    xt
    -0.08
    ver
    -0.06
    (int
    -0.04
    b
    -0.03
     current
    -0.02
    i
    -0.02
    args
    -0.02
    Ŀ
    -0.02
    import
    -0.01
    POSITIVE LOGITS
    A
    0.09
     A
    0.08
    er
    0.06
    _al
    0.05
     pass
    0.05
    gment
    0.04
    gle
    0.04
    į
    0.04
    ger
    0.04
    g
    0.04
    Activations Density 50.946%

    No Known Activations