© 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. 2824
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    tuple unpacking (negative activations)

    python-code · gemini-2.5-flash-lite

    opening parenthesis `(`

    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
     found
    -0.04
    ist
    -0.04
    None
    -0.04
    alse
    -0.03
    udoku
    -0.03
     None
    -0.03
     []↵↵
    -0.03
    atus
    -0.03
     False
    -0.03
     []↵
    -0.03
    POSITIVE LOGITS
    .write
    0.05
    (line
    0.05
    .read
    0.04
    hild
    0.03
    _neighbor
    0.02
     new
    0.02
    strip
    0.02
    hildren
    0.02
    _ne
    0.02
    (new
    0.02
    Activations Density 64.762%

    No Known Activations