© 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. 5901
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    dictionary comprehension key-value separator

    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
     Testing
    -0.07
     Test
    -0.06
    (self
    -0.05
    ).
    -0.04
     typing
    -0.04
     self
    -0.04
     {}↵↵
    -0.04
    [int
    -0.04
    Ö
    -0.04
    self
    -0.03
    POSITIVE LOGITS
    mport
    0.06
    rior
    0.05
    lose
    0.05
    uration
    0.04
    ies
    0.04
    alue
    0.03
    ness
    0.03
    endencies
    0.03
    append
    0.03
    ault
    0.03
    Activations Density 22.371%

    No Known Activations