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

    Neuronpedia

    INDEX
    Explanations

    names followed by comma

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     বহন
    0.38
    itate
    0.38
    ார்க்க
    0.38
     kto
    0.37
    ongyang
    0.36
    겠죠
    0.35
     utili
    0.35
    util
    0.35
    itution
    0.35
     aDecoder
    0.35
    POSITIVE LOGITS
     ơi
    0.61
    님
    0.54
     thank
    0.53
     dear
    0.51
     তুমি
    0.50
     please
    0.48
    !
    0.47
     спасибо
    0.46
     你
    0.45
    ရေ
    0.45
    Act Density 0.027%

    No Known Activations