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

    Neuronpedia

    INDEX
    Explanations

    important notes and disclaimers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     क्रमशः
    0.28
     çeşitli
    0.27
     तसेच
    0.25
     તેમજ
    0.25
     می‌باشد
    0.24
     Vielzahl
    0.24
     العديد
    0.24
     sekä
    0.24
     illetve
    0.24
     ranging
    0.24
    POSITIVE LOGITS
    ：
    0.66
    :
    0.63
    *:
    0.45
    ៖
    0.44
    ):
    0.43
    ":
    0.40
     rằng
    0.40
    +:
    0.40
     :
    0.39
    ：“
    0.39
    Act Density 0.792%

    No Known Activations