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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenAI · Weight-Sparse Transformers
    5. CircuitGPT-Python
    7. MLP
    9. 6-MLP
    11. 3017
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    csv reader or writer

    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
    .split
    -0.03
    .strip
    -0.02
    er
    -0.01
    ile
    -0.01
     heapq
    -0.01
    ra
    -0.01
    A
    -0.01
    u
    -0.01
     a
    -0.01
    _a
    -0.01
    POSITIVE LOGITS
    lose
    0.03
    append
    0.03
    ush
    0.02
    apping
    0.02
    rior
    0.02
                ↵
    0.02
            ↵
    0.02
     defaultdict
    0.02
    ([
    0.02
    lat
    0.02
    Activations Density 26.122%

    No Known Activations