© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenAI · Weight-Sparse Transformers
    5. CircuitGPT-Python
    7. MLP
    9. 2-MLP
    11. 3959
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    `from` keyword usage

    python-code · gemini-2.5-flash-lite

    function definition start (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
    Not in Any Lists

    No Comments

    Negative Logits
    ry
    -0.04
    con
    -0.03
    iti
    -0.03
     float
    -0.03
    ary
    -0.02
     int
    -0.02
    .con
    -0.02
    _matrix
    -0.02
    _per
    -0.02
     per
    -0.02
    POSITIVE LOGITS
     top
    0.04
    an
    0.04
    oard
    0.02
    aze
    0.02
    blem
    0.02
    grid
    0.02
    _grid
    0.02
     grid
    0.02
     graph
    0.02
    udoku
    0.02
    Activations Density 100.000%

    No Known Activations