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

    Neuronpedia

    INDEX
    Explanations

    French subjects and negation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    wenden
    0.93
     ornare
    0.90
     nachhalt
    0.89
     implementación
    0.89
     käyttö
    0.88
     شدند
    0.85
     protezione
    0.85
     ombil
    0.84
     tätig
    0.84
    ificar
    0.83
    POSITIVE LOGITS
     ne
    0.97
     y
    0.82
     ва
    0.79
     נ
    0.72
     se
    0.71
     n
    0.70
     soul
    0.68
     met
    0.66
     се
    0.66
     est
    0.66
    Act Density 0.033%

    No Known Activations