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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    \Mail
    -0.07
    下面是小
    -0.06
    epar
    -0.06
    -State
    -0.06
    欧式
    -0.06
    ꇴ
    -0.06
    ,error
    -0.06
    未知
    -0.06
    (BigDecimal
    -0.06
    ساب
    -0.06
    POSITIVE LOGITS
     puts
    0.07
     creators
    0.07
     humans
    0.07
     passwords
    0.07
    /*.
    0.07
    结局
    0.07
            ↵↵
    0.06
     ongoing
    0.06
     Apache
    0.06
     writers
    0.06
    Act Density 0.030%

    No Known Activations