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

    Neuronpedia

    INDEX
    Explanations

    Hark

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    近年来
    0.49
     verfügbar
    0.48
    mektedir
    0.48
     🌱
    0.46
    मुळे
    0.46
    产业
    0.45
    徜
    0.45
     rejuvenating
    0.44
    传承
    0.43
     repurposed
    0.43
    POSITIVE LOGITS
     trois
    0.66
     deux
    0.59
     two
    0.57
     three
    0.56
     zwei
    0.55
     tiga
    0.54
     drei
    0.53
     dois
    0.52
     dwóch
    0.52
     four
    0.51
    Act Density 0.016%

    No Known Activations