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

    Neuronpedia

    INDEX
    Explanations

    Literary genres and writing style

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     approves
    -0.09
     مراق
    -0.09
     కీల
    -0.08
     Aluminium
    -0.08
     സുരക്ഷ
    -0.08
     muita
    -0.08
     zákaz
    -0.08
     poko
    -0.08
     здоровья
    -0.08
     recycl
    -0.08
    POSITIVE LOGITS
     कविता
    0.11
    小说
    0.10
    形式
    0.10
     novels
    0.10
     prose
    0.10
    unstyled
    0.09
     작품
    0.09
    作品
    0.09
     protest
    0.09
     poetry
    0.09
    Act Density 0.045%

    No Known Activations