© 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. 2-MLP
    11. 4754
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    decorator argument 'str' or list assignment (negative activations)

    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
    _rate
    -0.12
    ange
    -0.07
    <
    -0.07
    \
    -0.06
    ;
    -0.06
    3
    -0.06
    2
    -0.06
    >
    -0.05
    4
    -0.05
    1
    -0.05
    POSITIVE LOGITS
    ]]↵
    0.13
    _by
    0.10
    )]↵
    0.10
    '↵
    0.09
     by
    0.08
    "↵
    0.08
     []↵
    0.08
    )↵
    0.08
    ake
    0.07
    }↵
    0.07
    Activations Density 26.205%

    No Known Activations