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

    Neuronpedia

    INDEX
    Explanations

    calculate proportional outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Dacă
    0.52
     усі
    0.43
     虽然
    0.43
    你会
    0.42
     Jeśli
    0.40
     ถ้า
    0.40
    Jeśli
    0.40
     当前
    0.40
     использу
    0.40
     Larry
    0.39
    POSITIVE LOGITS
     elucidation
    0.45
     auspicious
    0.44
     unforgettable
    0.43
     histological
    0.43
     centenary
    0.43
     invaluable
    0.43
     gastronomic
    0.43
     fruitful
    0.42
     satisfactorily
    0.42
     delicacies
    0.42
    Act Density 0.004%

    No Known Activations