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

    Neuronpedia

    INDEX
    Explanations

    Two

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    いただ
    -0.08
    `${
    -0.08
    лемент
    -0.08
    西宁
    -0.07
     reservoir
    -0.07
    :UIControlStateNormal
    -0.07
    влажн
    -0.07
    라고
    -0.07
    .curr
    -0.07
    בוט
    -0.07
    POSITIVE LOGITS
     two
    0.10
     zwei
    0.08
     nine
    0.08
    Two
    0.08
     fünf
    0.08
     Four
    0.08
     seven
    0.08
     one
    0.08
     four
    0.08
     Two
    0.07
    Act Density 0.168%

    No Known Activations