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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    后
    -0.07
     torn
    -0.06
     desde
    -0.06
     však
    -0.06
    так
    -0.06
     gitti
    -0.06
    ypsum
    -0.06
     jejich
    -0.06
     governo
    -0.06
     سلام
    -0.06
    POSITIVE LOGITS
     Environment
    0.07
    動
    0.07
    direction
    0.07
    ैं।↵
    0.06
     ROOT
    0.06
     Image
    0.06
     Ebony
    0.06
    itan
    0.06
     regulated
    0.06
     имя
    0.06
    Act Density 0.000%

    No Known Activations