© 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. 2-MLP
    11. 7495
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    string literal assignment or comparison

    python-code · gemini-2.5-flash-lite

    left shift assignment (negative activations)

    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
     dp
    -0.11
    _comb
    -0.07
     sorted
    -0.05
    _counts
    -0.05
     possible
    -0.04
     Returns
    -0.04
    [n
    -0.04
     comb
    -0.04
    chedule
    -0.04
    ))
    -0.04
    POSITIVE LOGITS
     //
    0.07
     [[
    0.07
    _value
    0.06
     Value
    0.06
    /
    0.06
     values
    0.06
     value
    0.06
    _values
    0.06
    value
    0.06
     ((
    0.06
    Activations Density 100.000%

    No Known Activations