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

    Neuronpedia

    INDEX
    Explanations

    Russian words and phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pourra
    0.66
     sämt
    0.66
     কিংবা
    0.65
     tiap
    0.60
     podremos
    0.59
     تمامی
    0.59
     bzw
    0.57
     turut
    0.57
     integrantes
    0.57
     pourront
    0.57
    POSITIVE LOGITS
    ́
    0.75
     않습니다
    0.67
     것입니다
    0.66
    ೕ
    0.64
    ോ
    0.63
    있다
    0.63
    ౖ
    0.63
     اثنين
    0.62
     वहाँ
    0.60
     అతను
    0.59
    Act Density 0.007%

    No Known Activations