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

    Neuronpedia

    INDEX
    Explanations

    Kitco, WebMD, Korea Times, EaseUS, Wilmar International

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    il
    0.72
    ీ
    0.69
    ra
    0.65
     elongate
    0.63
    어나
    0.62
    rishna
    0.62
     Planck
    0.61
     W
    0.61
    岄
    0.60
    ados
    0.60
    POSITIVE LOGITS
     for
    1.52
     in
    1.41
     be
    1.31
     have
    1.10
    在
    1.06
    も
    1.06
     can
    1.03
     σε
    0.98
    도
    0.97
     of
    0.89
    Act Density 0.006%

    No Known Activations