© 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. 3149
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    assignment or length checks (negative activations)

    python-code · gemini-2.5-flash-lite

    `dictionary` or `sides` attribute access

    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
     between
    -0.05
    loat
    -0.05
    oard
    -0.04
    aze
    -0.04
    blem
    -0.04
    grid
    -0.04
    _grid
    -0.04
     grid
    -0.04
     graph
    -0.04
    udoku
    -0.04
    POSITIVE LOGITS
    visited
    0.06
     visited
    0.06
    isited
    0.05
    rontier
    0.04
    .path
    0.04
    ag
    0.04
    join
    0.03
     dfs
    0.03
    queue
    0.03
    ig
    0.02
    Activations Density 99.966%

    No Known Activations