© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenAI · Weight-Sparse Transformers
    5. CircuitGPT-Python
    7. MLP
    9. 6-MLP
    11. 5418
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    constructor arguments (negative activations)

    python-code · gemini-2.5-flash-lite

    print function call beginning

    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
    -0.04
    (str
    -0.04
    e
    -0.03
    lambda
    -0.03
    _result
    -0.03
    result
    -0.02
    (int
    -0.02
    mmon
    -0.02
    ce
    -0.02
    output
    -0.02
    POSITIVE LOGITS
     dp
    0.05
    _comb
    0.03
     main
    0.03
    _counts
    0.03
     solve
    0.03
     possible
    0.03
    .set
    0.03
     comb
    0.02
    _sum
    0.02
    inations
    0.02
    Activations Density 91.997%

    No Known Activations