© 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. 2364
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    'not in' statement checks (negative activations)

    python-code · gemini-2.5-flash-lite

    re.match

    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
    init
    -0.03
    itial
    -0.03
    ctor
    -0.02
    _grid
    -0.02
    ().
    -0.02
    py
    -0.02
     Initialize
    -0.01
    structions
    -0.01
    dule
    -0.01
     grid
    -0.01
    POSITIVE LOGITS
    lse
    0.04
    lif
    0.04
     if
    0.03
     elif
    0.03
     If
    0.03
    if
    0.03
    _with
    0.03
     found
    0.02
    ist
    0.02
     Check
    0.02
    Activations Density 55.298%

    No Known Activations