© 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. 6105
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    function definition parameter or default value

    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
    .txt
    -0.04
     '
    -0.03
    un
    -0.03
     "
    -0.02
     each
    -0.02
    _f
    -0.02
    ves
    -0.02
    as
    -0.02
    ed
    -0.01
     =
    -0.01
    POSITIVE LOGITS
    .is
    0.07
    .num
    0.07
    .in
    0.06
    ..
    0.05
    out
    0.04
    .heapp
    0.04
     file
    0.04
    ho
    0.04
    ().
    0.03
    qrt
    0.03
    Activations Density 22.354%

    No Known Activations