© 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. 4436
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    closing parenthesis `)` followed by `return` (negative activations)

    python-code · gemini-2.5-flash-lite

    raise exception 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
    (range
    -0.05
    range
    -0.04
    an
    -0.04
    ant
    -0.03
     range
    -0.03
    _an
    -0.03
    _range
    -0.03
     an
    -0.02
    20
    -0.02
    .txt
    -0.02
    POSITIVE LOGITS
     True
    0.04
    .name
    0.03
    .id
    0.03
    _idx
    0.02
    dex
    0.02
    .values
    0.02
    _a
    0.02
    _index
    0.01
     op
    0.01
    ef
    0.01
    Activations Density 76.090%

    No Known Activations