© 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. 4349
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    start of module or 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
    (range
    -0.07
    ][
    -0.05
    .append
    -0.04
    [(
    -0.04
     min
    -0.04
    rint
    -0.03
     for
    -0.03
     assign
    -0.03
     process
    -0.03
     path
    -0.03
    POSITIVE LOGITS
     al
    0.07
     in
    0.06
    .d
    0.06
     new
    0.05
     temp
    0.04
     dy
    0.04
     nx
    0.04
    ty
    0.04
     n
    0.03
    (n
    0.03
    Activations Density 14.017%

    No Known Activations