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

    Neuronpedia

    INDEX
    Explanations

    asking you to do

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    是
    0.30
    (
    0.27
    :
    0.27
    所有的
    0.25
     selaku
    0.25
     جميع
    0.24
     Старки
    0.24
     состоялась
    0.24
     এটি
    0.23
    хода
    0.23
    POSITIVE LOGITS
    u
    0.29
     whatnot
    0.29
    ine
    0.27
    renaline
    0.26
     exponential
    0.25
    த்துடன்
    0.25
    estream
    0.25
     don
    0.25
     chew
    0.24
    p
    0.24
    Act Density 3.389%

    No Known Activations