© 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. 5928
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    string literals or variable names (negative activations)

    python-code · gemini-2.5-flash-lite

    variable assignment comma separator

    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
     us
    -0.02
     between
    -0.02
    _d
    -0.02
     based
    -0.02
     on
    -0.02
    _di
    -0.02
     by
    -0.01
     that
    -0.01
    "
    -0.01
    _from
    -0.01
    POSITIVE LOGITS
    :↵
    0.02
    ':
    0.01
    ":
    0.01
    £
    0.01
    Ľ
    0.01
    ±
    0.01
    ²
    0.01
    «
    0.01
    #
    0.00
    +
    0.00
    Activations Density 59.054%

    No Known Activations