© 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. 7519
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    closing parenthesis of a function call

    python-code · gemini-2.5-flash-lite

    return value (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
     continue
    -0.08
    [str
    -0.08
    _v
    -0.06
    _string
    -0.06
    join
    -0.05
    90
    -0.05
    raw
    -0.05
    .split
    -0.05
     raise
    -0.05
     defaultdict
    -0.04
    POSITIVE LOGITS
     pro
    0.11
    (pro
    0.11
    _pro
    0.10
    pro
    0.09
    [n
    0.06
     ny
    0.05
    (list
    0.05
    ample
    0.05
    igh
    0.05
    (maze
    0.05
    Activations Density 100.000%

    No Known Activations