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

    Neuronpedia

    INDEX
    Explanations

    not necessarily

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     রাশিয়ার
    0.38
     intensive
    0.38
    だな
    0.37
    릭
    0.35
     vacancies
    0.35
     বলিউ
    0.34
    راح
    0.34
    mii
    0.34
     chalkboard
    0.34
     philanthropic
    0.34
    POSITIVE LOGITS
     сты
    0.44
    ^{-
    0.43
     &-
    0.41
     время
    0.41
     விட்டு
    0.41
    jitter
    0.41
    ETARY
    0.41
    unzione
    0.41
     proteína
    0.39
    fficacy
    0.39
    Act Density 0.001%

    No Known Activations