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

    Neuronpedia

    INDEX
    Explanations

    let's explain or break down

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    bilir
    0.68
     собою
    0.65
     upto
    0.63
    としての
    0.60
    пропетров
    0.59
    kA
    0.59
     ederim
    0.59
    多么
    0.58
     toa
    0.57
    되고
    0.57
    POSITIVE LOGITS
    ícia
    0.91
     me
    0.90
    icia
    0.87
     membahas
    0.84
     us
    0.84
     divisão
    0.83
     нас
    0.81
     осмо
    0.81
     स्टार्ट
    0.79
     derrot
    0.79
    Act Density 0.144%

    No Known Activations