© 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. 5021
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    digits within lists (negative activations)

    python-code · gemini-2.5-flash-lite

    except keyword

    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
    None
    -0.05
     defaultdict
    -0.04
    alse
    -0.04
     {}↵↵
    -0.04
    mport
    -0.04
     None
    -0.04
     {}↵
    -0.04
     []↵↵
    -0.04
     False
    -0.04
    his
    -0.04
    POSITIVE LOGITS
     given
    0.04
     between
    0.03
     spe
    0.03
     based
    0.02
     from
    0.02
     with
    0.02
    .split
    0.01
    ffe
    0.01
    h
    0.01
    )↵↵↵
    0.01
    Activations Density 99.454%

    No Known Activations