© 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. 4677
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    `in` keyword in condition (negative activations)

    python-code · gemini-2.5-flash-lite

    string slicing `b[x:y]`

    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
    ateg
    -0.05
     ((
    -0.03
    term
    -0.03
    ((
    -0.03
    zero
    -0.03
     [(
    -0.03
    over
    -0.03
     (
    -0.02
     char
    -0.02
    isi
    -0.02
    POSITIVE LOGITS
     &
    0.02
     are
    0.02
    etween
    0.02
     {}↵↵
    0.02
    ĭ
    0.02
     {}↵
    0.02
    _he
    0.02
     []↵↵
    0.01
    oth
    0.01
    verage
    0.01
    Activations Density 99.965%

    No Known Activations