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

    Neuronpedia

    INDEX
    Explanations

    you or your

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    的朋友
    0.47
    식회사
    0.44
     `>=`,
    0.43
     জানিয়ে
    0.39
    适用于
    0.39
     tends
    0.39
     `=`,
    0.38
     workmanship
    0.38
     tienden
    0.38
    úng
    0.37
    POSITIVE LOGITS
    you
    0.55
     உன்
    0.53
     nowe
    0.52
    your
    0.51
     тебе
    0.51
    あなたは
    0.51
     you
    0.50
     तुम
    0.49
     তুমি
    0.49
     тобой
    0.48
    Act Density 0.043%

    No Known Activations