© 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. 3853
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    recursive calls with arguments

    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
    .pop
    -0.03
    uild
    -0.03
     con
    -0.02
     read
    -0.02
     initial
    -0.02
     generate
    -0.02
    .de
    -0.02
    ],
    -0.02
    unction
    -0.01
     last
    -0.01
    POSITIVE LOGITS
    +
    0.06
     +
    0.05
     Create
    0.04
    0
    0.04
    div
    0.04
    append
    0.04
    itial
    0.04
     +=
    0.04
    [:
    0.03
    stance
    0.03
    Activations Density 44.944%

    No Known Activations