Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    Code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Parking
    -0.06
     Austr
    -0.06
    Deep
    -0.06
    林
    -0.06
    ration
    -0.06
    ABOUT
    -0.06
     Speedway
    -0.06
     Parking
    -0.06
     Fletcher
    -0.06
    orphic
    -0.06
    POSITIVE LOGITS
    published
    0.07
    /react
    0.07
     hated
    0.06
    /st
    0.06
    _points
    0.06
    الف
    0.06
    дии
    0.06
    (Expected
    0.06
    ,A
    0.06
    vised
    0.06
    Act Density 0.015%

    No Known Activations