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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     qr
    -0.07
     Boat
    -0.07
    地理
    -0.06
    .gt
    -0.06
    Ꮎ
    -0.06
    魔
    -0.06
     r
    -0.06
    办学
    -0.06
     imper
    -0.06
    翀
    -0.06
    POSITIVE LOGITS
    thinking
    0.07
    כביש
    0.07
    Sleep
    0.07
    звон
    0.07
     $('#'
    0.07
    פרויקט
    0.06
    비스
    0.06
    داف
    0.06
    옂
    0.06
    (SYS
    0.06
    Act Density 0.004%

    No Known Activations