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

    Neuronpedia

    INDEX
    Explanations

    citations and sources

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ตาม
    0.46
    oretically
    0.39
     everywhere
    0.39
     according
    0.38
    microsoft
    0.38
    PR
    0.38
    needed
    0.38
    +
    0.38
    ore
    0.37
    W
    0.37
    POSITIVE LOGITS
     loro
    0.61
     website
    0.60
     сайт
    0.58
     jejich
    0.57
     ಅವರ
    0.55
    他們的
    0.55
     classifies
    0.54
     advises
    0.54
    網站
    0.54
     বলছে
    0.53
    Act Density 0.013%

    No Known Activations