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

    Neuronpedia

    INDEX
    Explanations

    **,

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     derfor
    0.44
    SqlConnection
    0.43
    หรือ
    0.42
    lerden
    0.42
     සහ
    0.41
    뤽
    0.41
    anjutkan
    0.41
     किंवा
    0.40
    ziehungs
    0.40
    shr
    0.40
    POSITIVE LOGITS
    可以将
    0.52
     dnia
    0.49
     หาก
    0.47
     pokud
    0.46
     когато
    0.45
     when
    0.44
     I
    0.44
     $\
    0.44
     nếu
    0.44
    то
    0.43
    Act Density 0.002%

    No Known Activations