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

    Neuronpedia

    INDEX
    Explanations

    量

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     داشته
    -0.07
     вза
    -0.07
     that
    -0.07
    /loose
    -0.06
     disciples
    -0.06
     наприклад
    -0.06
     buckle
    -0.06
     какой
    -0.06
     Clippers
    -0.06
    驶
    -0.06
    POSITIVE LOGITS
     HAR
    0.06
    Four
    0.06
     Serie
    0.06
    뉴
    0.06
    .$
    0.06
     ク
    0.06
    ("/{
    0.06
    元素
    0.05
    ANCH
    0.05
    242
    0.05
    Act Density 0.091%

    No Known Activations