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

    Neuronpedia

    INDEX
    Explanations

    数据

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -0.08
     ч
    -0.08
    ，一
    -0.08
     яке
    -0.07
    Itr
    -0.07
    irap
    -0.07
    (has
    -0.07
    াৰত
    -0.07
     төмен
    -0.07
     lowering
    -0.07
    POSITIVE LOGITS
     smarter
    0.09
    ;
↵
↵
↵
    0.09
     actionable
    0.08
     желательно
    0.08
     sounding
    0.08
     Recommended
    0.08
     recommended
    0.08
     recomendable
    0.08
     opinion
    0.08
     doporu
    0.07
    Act Density 0.004%
    No Known Activations