© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenAI · Weight-Sparse Transformers
    5. CircuitGPT-Python
    7. MLP
    9. 6-MLP
    11. 3323
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    function call or definition arguments

    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
    ("
    -0.07
    ('
    -0.06
     Tuple
    -0.06
     "
    -0.05
     None
    -0.05
     default
    -0.05
     '
    -0.04
     False
    -0.04
    ['
    -0.04
    ault
    -0.03
    POSITIVE LOGITS
    join
    0.08
     Par
    0.03
     import
    0.03
    ser
    0.03
    h
    0.02
    ake
    0.02
    igh
    0.02
    ator
    0.02
    isit
    0.02
     y
    0.02
    Activations Density 57.350%

    No Known Activations