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

    Neuronpedia

    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. 4978
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    function calls or built-in functions (negative activations)

    python-code · gemini-2.5-flash-lite

    assigning attribute target

    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
    arehouse
    -0.03
    udent
    -0.03
    light
    -0.03
    uild
    -0.03
    .random
    -0.03
    stac
    -0.02
    liver
    -0.02
    rontier
    -0.02
    mployee
    -0.02
    ruck
    -0.02
    POSITIVE LOGITS
     },↵
    0.04
    =
    0.04
    ='
    0.03
    ="
    0.03
     ]↵
    0.03
     def
    0.03
     {'
    0.03
     {"
    0.03
    |
    0.02
     """↵
    0.02
    Activations Density 99.265%

    No Known Activations