© 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. 2335
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    second argument of a method definition (negative activations)

    python-code · gemini-2.5-flash-lite

    assignment or comparison operator

    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
     break
    -0.09
    der
    -0.05
     P
    -0.03
    P
    -0.03
    s
    -0.02
    .pop
    -0.01
    _p
    -0.01
     &
    -0.01
     ad
    -0.01
     else
    -0.01
    POSITIVE LOGITS
    1
    0.02
    .heapp
    0.02
    .parent
    0.02
    place
    0.02
     float
    0.02
    >
    0.01
     ob
    0.01
     str
    0.01
    D
    0.01
     !=
    0.01
    Activations Density 55.557%

    No Known Activations