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
     insanely
    0.49
     crappy
    0.42
     teilweise
    0.42
     দুইজন
    0.41
    有点
    0.41
     scary
    0.40
     gotta
    0.40
     сложно
    0.40
     частично
    0.40
    ್ರೆ
    0.39
    POSITIVE LOGITS
     wholly
    0.68
     entirely
    0.68
     fully
    0.66
     truly
    0.58
    完全
    0.57
     entièrement
    0.56
     pleinement
    0.56
     totalmente
    0.54
    完全に
    0.53
     wholeheartedly
    0.53
    Act Density 0.025%

    No Known Activations