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

    Neuronpedia

    INDEX
    Explanations

    de/the + noun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     it
    0.84
     the
    0.73
    它
    0.71
     It
    0.69
     this
    0.67
     its
    0.66
     there
    0.62
     hadn
    0.60
     dodgy
    0.60
     your
    0.59
    POSITIVE LOGITS
     оценка
    0.78
     эффективности
    0.69
     adaptability
    0.69
    ของการ
    0.66
     наличие
    0.65
    importanza
    0.64
    availability
    0.63
    asibility
    0.63
    ثير
    0.61
     unor
    0.60
    Act Density 0.313%

    No Known Activations