© 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. 4843
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    class definition and indentation (negative activations)

    python-code · gemini-2.5-flash-lite

    argument separator in method definitions

    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
     and
    -0.07
     &
    -0.05
     get
    -0.04
     Get
    -0.04
    get
    -0.04
    alculate
    -0.03
    ),↵
    -0.03
     parse
    -0.03
    .get
    -0.03
    enerate
    -0.03
    POSITIVE LOGITS
     |
    0.03
     %
    0.02
    ())
    0.01
    }↵
    0.01
    ~
    0.01
    ag
    0.01
    %
    0.01
    udoku
    0.01
    ta
    0.01
     ob
    0.01
    Activations Density 94.075%

    No Known Activations