© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenAI · Weight-Sparse Transformers
    5. CircuitGPT-Python
    7. MLP
    9. 6-MLP
    11. 5226
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    dictionary key-value pairs (negative activations)

    python-code · gemini-2.5-flash-lite

    insert or add method call

    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
    -0.04
    aze
    -0.04
    blem
    -0.04
    grid
    -0.03
    _grid
    -0.03
     grid
    -0.03
     graph
    -0.03
    udoku
    -0.03
     maze
    -0.03
    .grid
    -0.03
    POSITIVE LOGITS
    sed
    0.03
    ized
    0.03
    ble
    0.03
    ated
    0.03
    cted
    0.03
    ted
    0.02
    ied
    0.02
    vailable
    0.02
    ded
    0.02
    for
    0.02
    Activations Density 98.515%

    No Known Activations