© 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. 3250
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    method call argument access (negative activations)

    python-code · gemini-2.5-flash-lite

    attribute access or dictionary assignment

    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
    um
    -0.05
     plt
    -0.03
    orted
    -0.03
    apping
    -0.03
     defaultdict
    -0.02
    ([
    -0.02
    .s
    -0.02
     {}↵
    -0.02
    ctionary
    -0.02
     dict
    -0.02
    POSITIVE LOGITS
    if
    0.03
    (n
    0.02
    [n
    0.02
    (N
    0.02
    .split
    0.02
    (num
    0.02
     while
    0.02
     iter
    0.01
    :
    0.01
     _
    0.01
    Activations Density 94.453%

    No Known Activations