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

    Neuronpedia

    INDEX
    Explanations

    number of parameters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AL
    0.48
    ORY
    0.43
     bluetooth
    0.42
    of
    0.41
    OF
    0.41
    Du
    0.41
     Dukes
    0.41
    ক
    0.40
    初の
    0.40
    ا
    0.39
    POSITIVE LOGITS
    count
    0.79
     எண்ணிக்கை
    0.79
    数を
    0.77
     counted
    0.74
     sayısı
    0.74
     Anzahl
    0.72
    数は
    0.72
     count
    0.72
    সংখ্যা
    0.71
    数が
    0.71
    Act Density 0.144%

    No Known Activations