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

    Neuronpedia

    INDEX
    Explanations

    considerando diferentes, buscar las

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     vyber
    0.54
     privind
    0.54
     দেয়নি
    0.53
     উপভোগ
    0.53
     berühm
    0.52
     fazendo
    0.52
    Não
    0.50
     vyroben
    0.50
     valmist
    0.49
    fabric
    0.49
    POSITIVE LOGITS
     una
    0.98
     μια
    0.91
     un
    0.89
     ఒక
    0.83
     một
    0.79
     ஒரு
    0.79
     какую
    0.78
    一個
    0.78
     einen
    0.78
     ഒരു
    0.78
    Act Density 0.251%

    No Known Activations