© 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. 2737
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    comma after a variable (negative activations)

    python-code · gemini-2.5-flash-lite

    exception or after comma

    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
    .heapp
    -0.04
    _op
    -0.04
    arest
    -0.03
    |
    -0.03
    31
    -0.03
    21
    -0.03
    41
    -0.03
    61
    -0.03
     {}↵↵
    -0.03
    52
    -0.03
    POSITIVE LOGITS
    jkstra
    0.02
    ~
    0.02
     lat
    0.02
    les
    0.02
    %
    0.02
    is
    0.02
    udoku
    0.02
    ati
    0.01
    er
    0.01
     ob
    0.01
    Activations Density 92.054%

    No Known Activations