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

    Neuronpedia

    INDEX
    Explanations

    for

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -Le
    -0.07
     obten
    -0.07
     бок
    -0.07
    Updated
    -0.06
     Chand
    -0.06
    ysl
    -0.06
     søger
    -0.06
    ayette
    -0.06
    BMW
    -0.06
     ответ
    -0.06
    POSITIVE LOGITS
    ,SIGNAL
    0.07
     braz
    0.06
    olicy
    0.06
     "))↵
    0.06
    PictureBox
    0.06
    (Border
    0.06
     segregation
    0.06
    inear
    0.06
     cord
    0.06
     for
    0.06
    Act Density 0.002%

    No Known Activations