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

    Neuronpedia

    INDEX
    Explanations

    range(

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     senare
    0.89
    ದಲು
    0.85
    在高
    0.80
     prerequisite
    0.79
     masuk
    0.79
     guér
    0.77
     vient
    0.77
     correspondant
    0.76
     véritables
    0.75
    นำ
    0.75
    POSITIVE LOGITS
    ()\
    0.95
    。\
    0.93
    ătoare
    0.89
    ().
    0.87
    。
    0.86
     bagels
    0.83
    ()].
    0.81
    Ns
    0.80
     Geißler
    0.80
    ၈
    0.80
    Act Density 0.001%

    No Known Activations