© 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. 6164
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    dictionary key access (negative activations)

    python-code · gemini-2.5-flash-lite

    string literal 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
    ["
    -0.03
    ['
    -0.03
    lse
    -0.02
    lif
    -0.02
     if
    -0.02
    V
    -0.02
     elif
    -0.02
     If
    -0.02
    if
    -0.02
    ]['
    -0.02
    POSITIVE LOGITS
     represe
    0.03
     representing
    0.03
     represent
    0.03
    22
    0.02
     ""
    0.02
    uples
    0.02
     Returns
    0.02
     contain
    0.02
     Example
    0.01
     whe
    0.01
    Activations Density 98.217%

    No Known Activations