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

    Neuronpedia

    INDEX
    Explanations

    higher/lower

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ..</
    0.65
     ওপর
    0.61
    ফলে
    0.60
     anschließend
    0.59
     THEN
    0.59
     trên
    0.58
     сверху
    0.58
     execute
    0.56
     gateways
    0.56
     downstream
    0.55
    POSITIVE LOGITS
    this
    0.82
    these
    0.68
    such
    0.66
     многих
    0.66
     тази
    0.66
    此类
    0.64
    we
    0.63
    the
    0.63
    si
    0.63
    sum
    0.63
    Act Density 0.119%

    No Known Activations