© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 4088
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    _by keyword for filtering

    python-code · gemini-2.5-flash-lite

    type casting or function arguments (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
    ize
    -0.05
     loc
    -0.05
    ilities
    -0.05
    pected
    -0.05
     base
    -0.05
    iz
    -0.05
    cep
    -0.05
    <extra_output_id:2047>
    -0.05
    apac
    -0.04
    None
    -0.04
    POSITIVE LOGITS
     dp
    0.07
    cond
    0.06
    inal
    0.06
    gram
    0.06
    inations
    0.06
    print
    0.06
    strip
    0.06
    rite
    0.06
    lit
    0.06
    ination
    0.06
    Activations Density 100.000%

    No Known Activations