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

    Neuronpedia

    INDEX
    Explanations

    class

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (cljs
    -0.07
    不忍
    -0.07
    遺
    -0.07
     Amar
    -0.07
    <i
    -0.07
     Ju
    -0.07
     sinus
    -0.07
     overcome
    -0.07
    ao
    -0.07
    條
    -0.06
    POSITIVE LOGITS
    ')->__('
    0.07
    成交
    0.07
    ˒
    0.07
    ()='
    0.06
     mieszkańców
    0.06
    峰会
    0.06
    wishlist
    0.06
     therein
    0.06
    睐
    0.06
    станавли
    0.06
    Act Density 0.000%

    No Known Activations