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

    Neuronpedia

    INDEX
    Explanations

    timetable or location

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ਹੈ
    0.54
     ہے
    0.50
    㑬
    0.49
     permettent
    0.49
     eikä
    0.49
     بوده
    0.48
     নিয়েছে
    0.47
     হয়েছে
    0.47
     موسیقی
    0.47
     ഇത്
    0.46
    POSITIVE LOGITS
    نا
    0.46
     Located
    0.43
    其他
    0.41
    V
    0.41
     Knot
    0.40
     Realtor
    0.39
     Arsenal
    0.39
    تن
    0.39
     Intelligence
    0.39
     Atlas
    0.39
    Act Density 0.003%

    No Known Activations