© 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. 3438
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    attribute access or assignment (negative activations)

    python-code · gemini-2.5-flash-lite

    max function with key argument

    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
    ,↵
    -0.03
     dp
    -0.02
    V
    -0.02
    ,
    -0.02
     V
    -0.02
    ][
    -0.02
    (range
    -0.02
    _comb
    -0.02
    range
    -0.01
    _counts
    -0.01
    POSITIVE LOGITS
    (len
    0.03
     len
    0.02
    len
    0.02
    :↵
    0.01
    .values
    0.01
    .s
    0.01
    _ob
    0.01
     cont
    0.01
     =
    0.01
    ource
    0.00
    Activations Density 96.767%

    No Known Activations