© 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. 2-MLP
    11. 5783
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    variable name sum (negative activations)

    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
    _dep
    -0.05
    umn
    -0.05
    que
    -0.05
    _un
    -0.05
    (con
    -0.05
     depth
    -0.05
     dep
    -0.05
     main
    -0.04
    ox
    -0.04
    main
    -0.03
    POSITIVE LOGITS
    [-
    0.05
     ValueError
    0.05
    |>
    0.04
    mbol
    0.04
    "{
    0.04
     enumerate
    0.04
    ._
    0.04
    fset
    0.04
    _counts
    0.04
     self
    0.04
    Activations Density 94.382%

    No Known Activations