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

    Neuronpedia

    INDEX
    Explanations

    you could say

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    اتو
    0.42
    REQUI
    0.41
     whatnot
    0.39
    μοσ
    0.38
    とにかく
    0.38
    ेटिक
    0.37
     परिभाषित
    0.37
    とりあえず
    0.36
    ‿
    0.36
    जू
    0.36
    POSITIVE LOGITS
     notice
    0.61
     noticed
    0.57
     wondered
    0.55
     wondering
    0.53
     probably
    0.52
     interested
    0.52
     see
    0.50
     oído
    0.49
     Notice
    0.49
     لاحظ
    0.48
    Act Density 0.009%

    No Known Activations