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

    Neuronpedia

    INDEX
    Explanations

    up

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     up
    -2.84
    up
    -1.96
     Up
    -1.96
    Up
    -1.90
     upto
    -1.35
     UP
    -1.26
    UP
    -1.12
    upto
    -1.11
    アップ
    -1.03
    ups
    -1.01
    POSITIVE LOGITS
    !*\
    0.66
     BoxDecoration
    0.60
     للمعارف
    0.60
    /*
    0.59
    athyroid
    0.57
    (!__
    0.56
    esModule
    0.54
    
    0.54
     Perfon
    0.52
     perspiration
    0.52
    Act Density 0.082%

    No Known Activations