© 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. 2144
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    part of method calls or keyword arguments (negative activations)

    python-code · gemini-2.5-flash-lite

    `v` followed by `[`

    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
     find
    -0.05
    .find
    -0.05
     Find
    -0.05
    ind
    -0.05
     found
    -0.04
    arch
    -0.03
     I
    -0.03
    ound
    -0.03
    _search
    -0.02
    iven
    -0.02
    POSITIVE LOGITS
     based
    0.04
    _rate
    0.03
    for
    0.02
    [-
    0.02
    [:
    0.02
    ron
    0.02
    [i
    0.01
     heap
    0.01
    imum
    0.01
     heapq
    0.01
    Activations Density 90.975%

    No Known Activations