© 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. 4174
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    function call arguments (negative activations)

    python-code · gemini-2.5-flash-lite

    parentheses or underscores in method definitions

    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
     representing
    -0.03
     that
    -0.02
     given
    -0.02
    ],
    -0.02
     each
    -0.02
     the
    -0.02
    ]][
    -0.02
     represe
    -0.02
    '],
    -0.02
    ).
    -0.02
    POSITIVE LOGITS
     True
    0.05
     None
    0.04
     False
    0.04
     []↵↵
    0.03
     },↵
    0.03
    None
    0.03
    V
    0.03
     []↵
    0.03
    alse
    0.03
     V
    0.03
    Activations Density 84.667%

    No Known Activations