© 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. 5975
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    method calls and attribute access

    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
    for
    -0.05
     based
    -0.05
    _rate
    -0.04
     |
    -0.04
     for
    -0.04
    join
    -0.04
    None
    -0.03
     any
    -0.03
     len
    -0.03
     ""
    -0.03
    POSITIVE LOGITS
    .find
    0.09
     find
    0.07
     Find
    0.07
    ind
    0.06
     found
    0.05
    arch
    0.04
     Get
    0.04
    ound
    0.04
    iven
    0.03
    (f
    0.03
    Activations Density 30.084%

    No Known Activations