© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenAI · Weight-Sparse Transformers
    5. CircuitGPT-Python
    7. MLP
    9. 6-MLP
    11. 4403
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    `.` or `(` after `self`

    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
    -0.06
     find
    -0.05
     Find
    -0.05
    ind
    -0.04
     found
    -0.04
    ro
    -0.03
    .parent
    -0.03
    ĥ
    -0.03
    arch
    -0.03
     problem
    -0.02
    POSITIVE LOGITS
    ran
    0.06
    ong
    0.05
     ran
    0.05
    [c
    0.05
     +=
    0.05
    (c
    0.04
    .ran
    0.04
     <
    0.04
    .position
    0.03
     based
    0.03
    Activations Density 25.705%

    No Known Activations