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

    Neuronpedia

    INDEX
    Explanations

    order

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     RoutedEventArgs
    -0.09
    -serif
    -0.08
    Drag
    -0.08
    封建
    -0.07
     revolution
    -0.07
    Scheduled
    -0.07
    原始
    -0.07
    ㅡ
    -0.07
     чуть
    -0.07
     Lil
    -0.07
    POSITIVE LOGITS
    allocator
    0.07
    ﴍ
    0.07
    invoices
    0.06
     Groups
    0.06
    뼝
    0.06
    أسباب
    0.06
    Sex
    0.06
    pecific
    0.06
    emony
    0.06
    잭
    0.06
    Act Density 0.025%

    No Known Activations