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

    Neuronpedia

    INDEX
    Explanations

    methods or steps

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     为了
    0.49
     হইলেও
    0.43
    毫无
    0.41
     vítima
    0.41
    由于
    0.40
    透过
    0.40
    版本的
    0.40
    实的
    0.39
     DRAM
    0.39
     Serious
    0.38
    POSITIVE LOGITS
    ite
    0.72
     are
    0.71
     galore
    0.66
    um
    0.65
     and
    0.59
    6
    0.58
    с
    0.58
    ize
    0.57
    і
    0.57
     extraordinaire
    0.55
    Act Density 0.081%

    No Known Activations