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

    Neuronpedia

    INDEX
    Explanations

    recur

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    今は
    -0.08
    _limits
    -0.07
     pleasure
    -0.07
     know
    -0.07
    饽
    -0.07
     keyof
    -0.07
    没问题
    -0.07
    oce
    -0.07
    琯
    -0.06
     boredom
    -0.06
    POSITIVE LOGITS
     Bul
    0.07
    标题
    0.07
    bmp
    0.06
    unread
    0.06
    .token
    0.06
     довольно
    0.06
    硬盘
    0.06
     adventurers
    0.06
    eated
    0.06
    ##_
    0.06
    Act Density 0.616%

    No Known Activations