© 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. 5520
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    function call arguments (negative activations)

    python-code · gemini-2.5-flash-lite

    initializing a set

    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
     cost
    -0.02
    &
    0.00
    #
    0.00
    '
    0.00
    *
    0.00
    %
    0.00
    )
    0.00
    !
    0.00
    "
    0.00
    $
    0.00
    POSITIVE LOGITS
    dict
    0.04
    uple
    0.04
     dict
    0.03
    0.02
     =
    0.02
    <extra_output_id:2047>
    0.02
    '
    0.00
    #
    0.00
    &
    0.00
    %
    0.00
    Activations Density 92.813%

    No Known Activations