© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenAI · Weight-Sparse Transformers
    5. CircuitGPT-Python
    7. MLP
    9. 2-MLP
    11. 4853
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    `continue` statement in loops

    python-code · gemini-2.5-flash-lite

    list slicing index (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
     ==
    -0.06
     *
    -0.06
     locations
    -0.05
    *
    -0.05
     location
    -0.05
    ck
    -0.05
    isi
    -0.04
    arch
    -0.04
    roup
    -0.04
    í
    -0.04
    POSITIVE LOGITS
     __
    0.06
    __(
    0.05
    neighbor
    0.05
    ighbor
    0.05
    (neighbor
    0.04
    [start
    0.04
    ice
    0.04
     Graph
    0.04
    isit
    0.04
    (start
    0.04
    Activations Density 100.000%

    No Known Activations