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

    Neuronpedia

    INDEX
    Explanations

    foreign roots

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Puoi
    0.47
     RetValue
    0.43
     możesz
    0.43
     Você
    0.42
     tienes
    0.42
     میشود
    0.42
     你
    0.40
     Diagnosis
    0.40
     ہوگئی
    0.40
     দৈত্য
    0.39
    POSITIVE LOGITS
    ς
    0.44
    ы
    0.41
    Ꮻ
    0.40
    </h3>
    0.39
     on
    0.38
    ◸
    0.38
     whirl
    0.38
    𝘶
    0.38
     удар
    0.37
     своими
    0.37
    Act Density 0.138%

    No Known Activations