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

    Neuronpedia

    INDEX
    Explanations

    welcome to the world

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    !
    0.52
     for
    0.43
    ！
    0.43
     ern
    0.40
    bind
    0.38
     dieser
    0.38
     değerli
    0.38
     onto
    0.37
    for
    0.37
     tejto
    0.37
    POSITIVE LOGITS
     الجدول
    0.47
    Yesterday
    0.46
    commonByteArray
    0.44
    Sorry
    0.43
     перебу
    0.42
     તાલુ
    0.42
     FYI
    0.42
     ജില്ല
    0.42
    Congratulations
    0.41
    出道
    0.41
    Act Density 0.003%

    No Known Activations