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

    Neuronpedia

    INDEX
    Explanations

    information and links

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     clavier
    0.38
    できるように
    0.38
    だけに
    0.36
     प्रश
    0.35
     പ്രാ
    0.35
     오늘은
    0.34
    міна
    0.34
    Kita
    0.34
    にかく
    0.33
    வ்வளவு
    0.33
    POSITIVE LOGITS
     HERE
    1.05
    HERE
    0.89
     here
    0.89
     ഇവിടെ
    0.78
     https
    0.76
     અહીં
    0.76
     здесь
    0.73
    here
    0.71
     هنا
    0.71
     тут
    0.71
    Act Density 0.043%

    No Known Activations