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

    Neuronpedia

    INDEX
    Explanations

    0

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    aoke
    -0.08
    处置
    -0.08
    炎
    -0.08
     thiệu
    -0.08
    辩
    -0.07
    念
    -0.07
    任
    -0.07
    ϑ
    -0.07
    鞠
    -0.07
    鹘
    -0.07
    POSITIVE LOGITS
    🛶
    0.07
    콱
    0.07
     strchr
    0.07
    小男孩
    0.07
    젴
    0.07
    这只
    0.07
    ניים
    0.06
    benchmark
    0.06
     Başkanlığı
    0.06
    .DependencyInjection
    0.06
    Act Density 0.002%

    No Known Activations