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

    Neuronpedia

    INDEX
    Explanations

    current state, status, or approach

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ও
    0.63
     electrón
    0.53
    י
    0.53
    原理
    0.52
    変換
    0.52
    も
    0.50
     largas
    0.49
    后
    0.49
    以后
    0.49
    도
    0.49
    POSITIVE LOGITS
     현재
    0.68
     huidige
    0.68
    on
    0.64
    目前的
    0.64
     फिलहाल
    0.60
    is
    0.59
    t
    0.56
    u
    0.56
    现状
    0.55
    Currently
    0.55
    Act Density 0.053%

    No Known Activations