© 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. 6-MLP
    11. 5102
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    dictionary assignment and unpacking (negative activations)

    python-code · gemini-2.5-flash-lite

    common keyword suffix `ing` or `ver`

    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
     it
    -0.20
    join
    -0.05
    oal
    -0.05
     each
    -0.05
    arehouse
    -0.04
    stination
    -0.04
    udent
    -0.04
    arget
    -0.04
    light
    -0.04
    uild
    -0.03
    POSITIVE LOGITS
     :
    0.09
    :
    0.04
    <extra_output_id:2047>
    0.03
    _i
    0.03
    import
    0.03
     ↵
    0.03
     e
    0.02
    Ã
    0.02
    _al
    0.02
    bs
    0.02
    Activations Density 99.987%

    No Known Activations