© 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. 5919
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    assignment operator (negative activations)

    python-code · gemini-2.5-flash-lite

    the plus operator or exponentiation

    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
    append
    -0.07
    .strip
    -0.05
    .add
    -0.05
    ush
    -0.05
     heapq
    -0.04
    .split
    -0.03
     path
    -0.03
     add
    -0.03
    add
    -0.03
    _path
    -0.03
    POSITIVE LOGITS
     {}↵↵
    0.04
     initial
    0.03
     {}↵
    0.03
    vai
    0.03
     []↵↵
    0.03
    .n
    0.03
     n
    0.03
     rows
    0.02
     dfs
    0.02
    (len
    0.02
    Activations Density 99.997%

    No Known Activations