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

    Neuronpedia

    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. 6011
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    assignment statements (negative activations)

    python-code · gemini-2.5-flash-lite

    .re strings and reverse operations

    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
    ateg
    -0.07
    ool
    -0.06
    ree
    -0.06
    ore
    -0.05
    ener
    -0.04
    (re
    -0.04
     heapq
    -0.03
    's
    -0.02
    ters
    -0.02
     as
    -0.02
    POSITIVE LOGITS
     dfs
    0.06
    che
    0.04
    put
    0.04
    loc
    0.03
    isit
    0.03
    ult
    0.03
    ci
    0.02
     he
    0.02
    hor
    0.02
     stack
    0.02
    Activations Density 99.931%

    No Known Activations