© 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. 2-MLP
    11. 6105
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    number in a list or dictionary

    python-code · gemini-2.5-flash-lite

    number literal 56 (negative activations)

    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
     dictionary
    -0.09
    ]['
    -0.08
    dict
    -0.08
    _co
    -0.07
    .values
    -0.06
     dict
    -0.06
    ctionary
    -0.06
    ['
    -0.06
     ↵
    -0.06
    _dict
    -0.06
    POSITIVE LOGITS
    .ran
    0.18
    .randint
    0.15
    .random
    0.12
    _shortest
    0.11
    .edges
    0.11
     Output
    0.10
    tem
    0.08
    arch
    0.07
    .num
    0.07
    _conne
    0.06
    Activations Density 100.000%

    No Known Activations