© 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. 3252
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    function argument or attribute (negative activations)

    python-code · gemini-2.5-flash-lite

    del keyword usage

    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
    .index
    -0.03
     ->
    -0.02
    e
    -0.01
    les
    -0.01
     whe
    -0.01
    _queue
    -0.01
     if
    -0.01
    ce
    -0.01
     for
    -0.01
    rontier
    -0.01
    POSITIVE LOGITS
    prese
    0.04
    .heapp
    0.03
    udoku
    0.02
    31
    0.02
    21
    0.02
    41
    0.02
    61
    0.02
    52
    0.02
    43
    0.02
    54
    0.02
    Activations Density 99.572%

    No Known Activations