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

    Neuronpedia

    INDEX
    Explanations

    further

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     कुनै
    0.52
    ﻟ
    0.52
    ുന്ന
    0.51
     hunch
    0.50
     celor
    0.49
     Voir
    0.49
    𝐬
    0.49
    𝐫
    0.48
    TACT
    0.48
    ிய
    0.48
    POSITIVE LOGITS
    spe
    0.49
     ench
    0.47
    酶
    0.44
    currentIndex
    0.44
    ρη
    0.44
     порядок
    0.44
    󠁢
    0.42
    উল্লেখ্য
    0.42
     promov
    0.42
    cí
    0.41
    Act Density 0.065%

    No Known Activations