© 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. 2-MLP
    11. 4057
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    function definition keyword `def` (negative activations)

    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
    umn
    -0.12
     dep
    -0.12
     depth
    -0.10
    _dep
    -0.10
     nx
    -0.07
     ny
    -0.06
    ep
    -0.06
    60
    -0.06
    -
    -0.06
    I
    -0.06
    POSITIVE LOGITS
    Á
    0.16
    ÷
    0.16
    À
    0.16
    ú
    0.16
    ø
    0.16
    þ
    0.16
    õ
    0.16
    ý
    0.16
    û
    0.16
    ÿ
    0.16
    Activations Density 69.757%

    No Known Activations