© 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. 4909
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    def and import statements

    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
    Node
    -0.06
    }:
    -0.06
    Ö
    -0.06
    set
    -0.05
    ly
    -0.05
     Testing
    -0.05
    import
    -0.05
     set
    -0.05
    Î
    -0.05
    St
    -0.05
    POSITIVE LOGITS
    xb
    0.06
    3
    0.05
    alculate
    0.04
    enerate
    0.03
     calculate
    0.03
     parse
    0.03
     generate
    0.03
     create
    0.02
     find
    0.02
    par
    0.02
    Activations Density 0.535%

    No Known Activations