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

    Neuronpedia

    INDEX
    Explanations

    therefore ,

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     그래도
    0.62
     però
    0.55
    注意的是
    0.54
     gdyż
    0.49
    しかし
    0.48
     toutefois
    0.48
     sillon
    0.46
     Ux
    0.46
     scoperta
    0.46
     мире
    0.45
    POSITIVE LOGITS
    forth
    0.54
     amikor
    0.54
    ledes
    0.51
     عندما
    0.48
    it
    0.48
    although
    0.46
    '
    0.46
    quando
    0.45
    oner
    0.44
    可以说
    0.44
    Act Density 0.013%

    No Known Activations