© 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. 2766
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    variable name in loop or function arguments (negative activations)

    python-code · gemini-2.5-flash-lite

    `len` function calls

    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
    oard
    -0.02
    aze
    -0.02
    blem
    -0.02
    grid
    -0.02
    _grid
    -0.02
     grid
    -0.02
     graph
    -0.02
    udoku
    -0.02
     maze
    -0.02
    .grid
    -0.02
    POSITIVE LOGITS
    ...
    0.03
    .
    0.01
    is
    0.01
    .f
    0.01
    .n
    0.01
    turn
    0.01
    ber
    0.01
     iter
    0.01
    unt
    0.01
    <extra_output_id:2047>
    0.01
    Activations Density 92.417%

    No Known Activations