© 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. 3297
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    **kwargs in function definition

    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
     abs
    -0.03
    ab
    -0.03
    Ī
    -0.03
    uple
    -0.03
    (map
    -0.02
    ti
    -0.02
     map
    -0.02
    ations
    -0.02
    ._
    -0.02
    list
    -0.01
    POSITIVE LOGITS
    args
    0.08
    w
    0.07
    £
    0.06
    K
    0.04
    _dict
    0.04
    param
    0.04
    _key
    0.04
    k
    0.03
    ke
    0.03
     k
    0.03
    Activations Density 50.013%

    No Known Activations