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

    Neuronpedia

    INDEX
    Explanations

    foreign articles meaning "a" or "one"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     you
    0.68
     başta
    0.61
     kojima
    0.57
     because
    0.57
     and
    0.55
     didn
    0.55
     with
    0.55
     +
    0.55
     there
    0.54
     লাগছে
    0.54
    POSITIVE LOGITS
     sebuah
    1.08
     ενός
    0.96
    Một
    0.93
    một
    0.93
     isang
    0.91
     една
    0.90
     seorang
    0.90
     một
    0.87
     ਇੱਕ
    0.86
     ఒక
    0.85
    Act Density 0.000%

    No Known Activations