© 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. 2-MLP
    11. 4125
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    Python slice with step -1

    python-code · gemini-2.5-flash-lite

    parts of common words (negative activations)

    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
     int
    -0.04
     /
    -0.03
    ↵            ↵
    -0.02
    ark
    -0.02
    ers
    -0.02
    rap
    -0.02
    ves
    -0.02
    ari
    -0.01
    ry
    -0.01
    ↵        ↵
    -0.01
    POSITIVE LOGITS
    -
    0.08
    __':↵
    0.06
    __
    0.06
    __(
    0.05
     __
    0.05
    __":↵
    0.05
     ↵
    0.03
     represent
    0.03
     input
    0.03
    stru
    0.02
    Activations Density 100.000%

    No Known Activations