© 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. 3984
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    method call argument separators (negative activations)

    python-code · gemini-2.5-flash-lite

    dictionary keys and values

    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
    inal
    -0.03
    result
    -0.03
    uel
    -0.03
    print
    -0.03
    sen
    -0.03
     result
    -0.03
    |
    -0.03
    _cost
    -0.03
    value
    -0.03
    (line
    -0.02
    POSITIVE LOGITS
     continue
    0.05
     for
    0.03
    get
    0.03
     get
    0.02
     return
    0.02
     temp
    0.02
    rc
    0.02
    .get
    0.02
    ype
    0.02
    type
    0.01
    Activations Density 99.989%

    No Known Activations