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

    Neuronpedia

    INDEX
    Explanations

    added or gives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    只能
    0.46
    IS
    0.46
    Authority
    0.41
    地域
    0.41
    RELAND
    0.41
    する必要があります
    0.40
    任何
    0.39
    VER
    0.39
    HER
    0.39
     любой
    0.39
    POSITIVE LOGITS
     geeft
    0.63
     zeigt
    0.55
     gives
    0.53
     added
    0.53
     sottoline
    0.53
     hilfre
    0.52
     coloquei
    0.52
     gave
    0.52
     добавлен
    0.52
     explic
    0.52
    Act Density 0.728%

    No Known Activations