© 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. 6191
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    class declaration or print statement (negative activations)

    python-code · gemini-2.5-flash-lite

    list comprehension converting to integer

    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
     dist
    -0.04
    alculate
    -0.04
     steps
    -0.03
    enerate
    -0.03
     calculate
    -0.03
     find
    -0.03
     parse
    -0.03
    co
    -0.03
     generate
    -0.03
    ri
    -0.03
    POSITIVE LOGITS
     def
    0.03
    [int
    0.02
    [t
    0.02
    [str
    0.02
    (
    0.02
    [s
    0.02
    [start
    0.02
    en
    0.01
     left
    0.01
     with
    0.01
    Activations Density 91.312%

    No Known Activations