© 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. 6087
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    assignment followed by list or value (negative activations)

    python-code · gemini-2.5-flash-lite

    index of list element

    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
    ]][
    -0.06
    ][
    -0.05
     [[
    -0.04
    loat
    -0.02
     if
    -0.02
    _edge
    -0.02
    ]['
    -0.02
     while
    -0.02
     If
    -0.02
     [↵
    -0.02
    POSITIVE LOGITS
    date
    0.05
    ink
    0.03
     Testing
    0.02
     Test
    0.02
    _grid
    0.02
    print
    0.02
    ]]
    0.01
    structions
    0.01
     {}↵
    0.01
     grid
    0.01
    Activations Density 92.104%

    No Known Activations