© 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. 6169
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    assignment to variable (negative activations)

    python-code · gemini-2.5-flash-lite

    sum of two squares

    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
    .name
    -0.04
    .id
    -0.03
    _idx
    -0.03
    dex
    -0.03
     [-
    -0.03
     between
    -0.02
    (len
    -0.02
    len
    -0.02
    mmon
    -0.02
     two
    -0.02
    POSITIVE LOGITS
     abs
    0.03
     I
    0.02
     Calculate
    0.02
    ([
    0.02
    etween
    0.02
    valid
    0.02
    sible
    0.01
    ab
    0.01
     (
    0.01
    ta
    0.01
    Activations Density 49.872%

    No Known Activations