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

    Neuronpedia

    INDEX
    Explanations

    proportions and fractions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ີ້
    0.37
    的不同
    0.36
     различными
    0.35
     unterschied
    0.34
     পারেন
    0.34
    uden
    0.34
     veřej
    0.34
     Insgesamt
    0.34
    ებში
    0.33
     கழக
    0.33
    POSITIVE LOGITS
     của
    0.65
     ofthe
    0.64
     của
    0.63
     மடங்கு
    0.61
    倍
    0.57
     של
    0.56
     倍
    0.54
    ของ
    0.52
     thereof
    0.50
     rispetto
    0.49
    Act Density 0.015%

    No Known Activations