© 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. 5137
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    closing parenthesis in function definition (negative activations)

    python-code · gemini-2.5-flash-lite

    list items

    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
     dist
    -0.05
     distances
    -0.05
     distance
    -0.04
     {}↵↵
    -0.03
     cost
    -0.03
     {}↵
    -0.02
    jkstra
    -0.02
     []↵↵
    -0.02
    .split
    -0.02
    ~
    -0.02
    POSITIVE LOGITS
    ty
    0.06
     -
    0.04
    ob
    0.04
    is
    0.03
    <extra_output_id:2047>
    0.02
    },↵
    0.02
     L
    0.02
     True
    0.01
    £
    0.01
    0.01
    Activations Density 99.945%

    No Known Activations