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

    Neuronpedia

    INDEX
    Explanations

    a lot of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    新的
    0.48
    ૃત
    0.47
    tsioon
    0.47
     gravida
    0.46
     Inhalte
    0.46
    的设计
    0.46
     Ayu
    0.44
    낳
    0.43
    照片
    0.43
    тья
    0.43
    POSITIVE LOGITS
     הם
    0.44
    Hor
    0.42
    am
    0.42
    ところが
    0.41
     милли
    0.41
    um
    0.41
    itat
    0.40
    ן
    0.39
     horrendous
    0.39
    чности
    0.39
    Act Density 0.002%

    No Known Activations