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

    Neuronpedia

    INDEX
    Explanations

    code definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    dai
    0.38
    lesssim
    0.37
    x
    0.37
    yler
    0.36
    这样的
    0.35
    لي
    0.35
     أد
    0.35
    يلي
    0.35
    empirical
    0.34
    وفي
    0.34
    POSITIVE LOGITS
    மையில்
    0.35
     الاعزاء
    0.35
     lard
    0.34
     duel
    0.32
     অভিনেত্র
    0.32
     servitude
    0.32
     tortue
    0.32
     bruise
    0.32
     яе
    0.32
     되었다
    0.32
    Act Density 0.006%

    No Known Activations