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

    Neuronpedia

    INDEX
    Explanations

    Korean or Japanese

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .bits
    -0.07
     itself
    -0.07
    困
    -0.06
     Hardy
    -0.06
    .prot
    -0.06
     مشکل
    -0.06
    στα
    -0.06
     Darkness
    -0.06
    vig
    -0.06
    rang
    -0.06
    POSITIVE LOGITS
     대한
    0.13
    への
    0.09
    での
    0.08
    tab
    0.07
    による
    0.07
     위한
    0.07
    =fopen
    0.06
     Ala
    0.06
     yönelik
    0.06
    进行
    0.06
    Act Density 0.005%

    No Known Activations