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

    Neuronpedia

    INDEX
    Explanations

    brand names and products

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ➢
    0.81
    тивний
    0.73
    ductory
    0.72
     Sobolev
    0.69
    0.69
     ascertaining
    0.68
     ờ
    0.68
    ittha
    0.67
    менение
    0.67
    0.66
    POSITIVE LOGITS
     няко
    0.69
    unless
    0.67
     innych
    0.65
    if
    0.65
     поколения
    0.65
    それ
    0.63
    যত
    0.61
     ทุก
    0.61
     जरूरतों
    0.59
    หรือไม่
    0.59
    Act Density 0.089%

    No Known Activations