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

    Neuronpedia

    INDEX
    Explanations

    positive adjectives

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    surname
    -0.08
     surname
    -0.08
     denominator
    -0.08
     breve
    -0.08
    оя
    -0.07
    letion
    -0.07
     Pim
    -0.07
     सित
    -0.07
    embros
    -0.07
    uiste
    -0.07
    POSITIVE LOGITS
    啊
    0.10
    <ul
    0.09
    呀
    0.09
    ર્ડ
    0.09
     görə
    0.08
    ありが
    0.08
     really
    0.08
     بالنسبة
    0.08
     alright
    0.08
     invaluable
    0.08
    Act Density 0.099%

    No Known Activations