© 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. 6192
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    print function calls (negative activations)

    python-code · gemini-2.5-flash-lite

    collections.Counter or collections.defaultdict

    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
     it
    -0.05
    from
    -0.04
    .split
    -0.03
    import
    -0.03
    0
    -0.03
    split
    -0.03
    .read
    -0.03
    .strip
    -0.03
     pass
    -0.03
    strip
    -0.02
    POSITIVE LOGITS
    /
    0.03
     :
    0.02
    ark
    0.02
     whe
    0.02
     /
    0.02
     //
    0.02
     color
    0.02
     label
    0.01
    List
    0.01
    riority
    0.01
    Activations Density 51.809%

    No Known Activations