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

    Neuronpedia

    INDEX
    Explanations

    list items or file names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    homme
    0.41
    เอา
    0.41
     absur
    0.40
     wholeheartedly
    0.39
     de
    0.39
     male
    0.38
     tormented
    0.38
     بھر
    0.38
    สำหรับการ
    0.38
     torment
    0.38
    POSITIVE LOGITS
    ；
    0.40
     regenv
    0.40
    рых
    0.40
     baryons
    0.40
    字节
    0.39
     catalyzes
    0.38
     catalysts
    0.38
     বোঝা
    0.38
    ខ្ញ
    0.38
    GLOBAL
    0.38
    Act Density 0.025%

    No Known Activations