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

    Neuronpedia

    INDEX
    Explanations

    identify

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     bánh
    -0.07
    是一种
    -0.07
     Nunes
    -0.07
    حمام
    -0.07
     verso
    -0.07
    万科
    -0.07
     بشأن
    -0.07
    /Input
    -0.06
    柒
    -0.06
     السيد
    -0.06
    POSITIVE LOGITS
     fatalities
    0.07
    _url
    0.07
     Müdürl
    0.07
    ♢
    0.07
    卉
    0.07
    ,buf
    0.06
     clubs
    0.06
     технолог
    0.06
     dob
    0.06
     وي
    0.06
    Act Density 0.030%

    No Known Activations