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

    Neuronpedia

    INDEX
    Explanations

    of the

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    着
    0.65
    اسو
    0.62
     oa
    0.62
    mettre
    0.62
    કની
    0.61
     ઘટના
    0.60
     আহমে
    0.60
    iveness
    0.60
    ocon
    0.60
    обходимо
    0.60
    POSITIVE LOGITS
     The
    1.47
    The
    1.31
     THE
    1.07
    ForThe
    1.06
     দ্য
    1.01
    THE
    0.99
     لل
    0.88
    OfThe
    0.88
    nThe
    0.87
     ofthe
    0.87
    Act Density 0.522%

    No Known Activations