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

    Neuronpedia

    INDEX
    Explanations

    dice and dominoes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     confid
    -0.09
     꿈
    -0.08
     대학
    -0.08
     대통령
    -0.08
     dieting
    -0.08
     관리자
    -0.08
    .Ang
    -0.08
    'imp
    -0.08
     Powered
    -0.07
     conflicting
    -0.07
    POSITIVE LOGITS
     tally
    0.15
     counting
    0.12
     Counting
    0.11
    Counting
    0.11
     количества
    0.11
     تعداد
    0.10
    (count
    0.10
     jumlah
    0.09
     nọmba
    0.09
     tatau
    0.09
    Act Density 0.017%

    No Known Activations