© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. OpenAI · Weight-Sparse Transformers
    5. CircuitGPT-Python
    7. MLP
    9. 2-MLP
    11. 3408
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    local keyword or within a word

    python-code · gemini-2.5-flash-lite

    dot or parenthesis preceding code elements (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
    ))
    -0.04
    _from
    -0.03
    _to
    -0.03
    ()
    -0.03
    ))<|
    -0.02
     to
    -0.02
     from
    -0.02
    ]]
    -0.02
    rom
    -0.02
    ake
    -0.02
    POSITIVE LOGITS
     dp
    0.07
    (maze
    0.05
     cell
    0.05
    (grid
    0.05
    _cell
    0.05
     cel
    0.05
    _cells
    0.05
    grid
    0.05
    udoku
    0.05
    [row
    0.05
    Activations Density 100.000%

    No Known Activations