© 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. 5455
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    list elements as strings (negative activations)

    python-code · gemini-2.5-flash-lite

    % len

    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
     model
    -0.04
    odel
    -0.04
    .add
    -0.03
    stance
    -0.03
    atus
    -0.03
    straint
    -0.02
    form
    -0.02
    tail
    -0.02
    ata
    -0.02
    straints
    -0.02
    POSITIVE LOGITS
     Calculate
    0.03
    etween
    0.02
    ines
    0.02
     abs
    0.02
    ven
    0.02
    ta
    0.02
    8
    0.02
     math
    0.02
    12
    0.02
    /
    0.01
    Activations Density 62.974%

    No Known Activations