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

    Neuronpedia

    INDEX
    Explanations

    mentions 'myself'

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    这也是
    0.30
     تقریباً
    0.30
     Fundraising
    0.30
     гораздо
    0.30
     सफलतापूर्वक
    0.30
     vrlo
    0.29
     досить
    0.29
    实时
    0.29
     sensiblement
    0.29
     প্রযুক্তি
    0.29
    POSITIVE LOGITS
     estrange
    0.38
     doubly
    0.36
     als
    0.33
    seudo
    0.33
     exot
    0.32
     other
    0.32
    ਏ
    0.31
     roul
    0.31
    L
    0.31
    both
    0.30
    Act Density 0.070%

    No Known Activations