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

    Neuronpedia

    INDEX
    Explanations

    indefinite articles and singular words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Pentru
    0.81
     Với
    0.78
     Tämä
    0.77
     Jeśli
    0.75
     Они
    0.74
     Для
    0.73
     Теперь
    0.73
    Pentru
    0.73
     Și
    0.72
     Dacă
    0.72
    POSITIVE LOGITS
     एक
    1.01
     einen
    1.00
     một
    0.97
     eine
    0.96
     een
    0.93
     একটি
    0.92
     μια
    0.89
    一個
    0.88
     ਇੱਕ
    0.87
     свои
    0.87
    Act Density 0.002%

    No Known Activations