© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenAI · Weight-Sparse Transformers
    5. CircuitGPT-Python
    7. MLP
    9. 6-MLP
    11. 4526
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    parentheses followed by print or assignment (negative activations)

    python-code · gemini-2.5-flash-lite

    closing parenthesis, bracket, or brace

    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
    .txt
    -0.07
     while
    -0.06
     iter
    -0.04
    _f
    -0.03
    as
    -0.03
    valid
    -0.02
    +
    -0.02
    sible
    -0.02
    ab
    -0.02
     steps
    -0.02
    POSITIVE LOGITS
    .is
    0.08
    .num
    0.07
    .name
    0.05
    .id
    0.05
     file
    0.05
     found
    0.05
    .in
    0.05
    _idx
    0.04
    dex
    0.04
    ..
    0.04
    Activations Density 96.651%

    No Known Activations