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

    Neuronpedia

    INDEX
    Explanations

    cannot and will not

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Если
    0.51
     vacaciones
    0.47
    Этот
    0.46
    朊
    0.46
     बीमारियों
    0.45
     праздник
    0.44
    獾
    0.44
     месяцев
    0.44
    个月
    0.43
     фигуры
    0.43
    POSITIVE LOGITS
    '
    0.44
     ausges
    0.41
     Authorized
    0.41
     dehuman
    0.41
     circumvent
    0.40
     quality
    0.40
     authorized
    0.40
    ulf
    0.40
    _
    0.40
     ä
    0.40
    Act Density 0.012%

    No Known Activations