© 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. 3019
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    function call arguments (negative activations)

    python-code · gemini-2.5-flash-lite

    re.match or re.fullmatch

    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
    hild
    -0.04
     other
    -0.04
    _neighbor
    -0.04
     new
    -0.04
    .split
    -0.03
    hildren
    -0.03
     between
    -0.03
    other
    -0.03
    ice
    -0.03
    _ne
    -0.03
    POSITIVE LOGITS
    _queue
    0.08
    rontier
    0.06
     heap
    0.06
    queue
    0.06
     collections
    0.06
    isit
    0.05
     queue
    0.05
    import
    0.05
    apping
    0.04
    ache
    0.04
    Activations Density 99.999%

    No Known Activations