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

    Neuronpedia

    INDEX
    Explanations

    issue

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ゜
    -0.07
    larınızı
    -0.07
    鼍
    -0.07
     polo
    -0.07
     Mandal
    -0.06
     Mang
    -0.06
     NUM
    -0.06
     prow
    -0.06
    管理条例
    -0.06
     atleast
    -0.06
    POSITIVE LOGITS
    Wię
    0.07
     Cri
    0.07
    .Future
    0.07
    апр
    0.07
    广阔
    0.07
    filter
    0.07
    тр
    0.07
    (cls
    0.07
    df
    0.07
     chấp
    0.07
    Act Density 0.006%

    No Known Activations