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

    Neuronpedia

    INDEX
    Explanations

    you, we, they + verb

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     очень
    0.45
     rất
    0.45
     অনে
    0.44
     também
    0.44
     cuja
    0.44
     более
    0.43
    also
    0.43
     эта
    0.43
     bastante
    0.41
    quite
    0.41
    POSITIVE LOGITS
     Normally
    0.43
     pueda
    0.41
     بتوان
    0.40
    想要的
    0.39
     Normalmente
    0.38
     normally
    0.37
     অবশিষ্ট
    0.37
    䅞
    0.36
    인
    0.36
    Ef
    0.36
    Act Density 0.014%

    No Known Activations