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

    Neuronpedia

    INDEX
    Explanations

    has/have been + ongoing state

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     došlo
    0.52
    发现了
    0.50
     принял
    0.41
     arose
    0.41
     begonnen
    0.40
     পেলাম
    0.40
     doš
    0.40
     получили
    0.39
     Lleg
    0.39
     או
    0.39
    POSITIVE LOGITS
     longstanding
    0.66
    ずっと
    0.64
     steadily
    0.61
    一直是
    0.59
     several
    0.58
    一直
    0.57
     since
    0.56
     sejak
    0.54
     beberapa
    0.54
     منذ
    0.53
    Act Density 0.004%

    No Known Activations