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

    Neuronpedia

    INDEX
    Explanations

    sometimes maybe optionally

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     абсолютно
    0.34
     absolutamente
    0.32
     meticul
    0.31
     sämt
    0.31
    はもちろん
    0.31
     unquestionably
    0.30
     mutlaka
    0.30
    毫无
    0.29
     völlig
    0.29
     především
    0.29
    POSITIVE LOGITS
    的一些
    0.32
    也可以
    0.29
     (?
    0.28
     (?)
    0.27
     eventuali
    0.27
    类似于
    0.27
     optionally
    0.26
    之类的
    0.26
     sometimes
    0.26
    maybe
    0.26
    Act Density 0.195%

    No Known Activations