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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    byn
    -0.06
    had
    -0.06
    .med
    -0.06
     Coy
    -0.06
    bai
    -0.06
    ystery
    -0.06
    ��
    -0.06
    weets
    -0.06
     任
    -0.06
     مف
    -0.06
    POSITIVE LOGITS
    [target
    0.07
    ,)↵
    0.07
    >")↵
    0.07
    ('\\
    0.07
    uario
    0.07
     تم
    0.06
    clado
    0.06
    �
    0.06
     ileri
    0.06
     мыш
    0.06
    Act Density 0.008%

    No Known Activations