© 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. 4222
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    `int` casting or type hinting (negative activations)

    python-code · gemini-2.5-flash-lite

    while keyword

    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
    mp
    -0.03
     valid
    -0.03
    Ö
    -0.03
     Testing
    -0.03
     Def
    -0.02
     Calculate
    -0.02
     Initialize
    -0.02
     Define
    -0.02
    Æ
    -0.02
    Ú
    -0.02
    POSITIVE LOGITS
     found
    0.05
    u
    0.04
     u
    0.04
    i
    0.03
    gs
    0.03
    a
    0.03
    for
    0.02
    over
    0.02
    k
    0.02
    _
    0.02
    Activations Density 83.961%

    No Known Activations