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

    Neuronpedia

    INDEX
    Explanations

    list separators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ώντας
    0.41
    作为一个
    0.41
    从而
    0.40
     በመ
    0.40
     fiind
    0.39
    是一种
    0.38
     poprzez
    0.38
     cites
    0.38
    izzando
    0.38
     dejando
    0.38
    POSITIVE LOGITS
     capable
    0.77
     designed
    0.75
     whose
    0.75
     cuya
    0.73
     devoid
    0.71
     steeped
    0.71
     riddled
    0.67
    designed
    0.66
     cuja
    0.65
     unrelated
    0.64
    Act Density 0.021%

    No Known Activations