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

    Neuronpedia

    INDEX
    Explanations

    foreign language or script

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ρ
    0.46
     operas
    0.46
     astral
    0.45
    ;
    0.45
     insensible
    0.44
     diarr
    0.44
     posibles
    0.44
     alde
    0.43
     analges
    0.43
    Tá
    0.43
    POSITIVE LOGITS
     പ്രതിഷേധ
    0.59
     বিজ্ঞাপন
    0.46
    文本
    0.46
    rashed
    0.46
    圧縮
    0.44
     බැ
    0.44
     ചോദ്യ
    0.44
    ഹ്ലാദ
    0.44
     விள
    0.43
     sic
    0.43
    Act Density 0.000%

    No Known Activations