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

    Neuronpedia

    INDEX
    Explanations

    differential equations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    沸
    -0.07
     vigorously
    -0.07
     الوقت
    -0.07
    歧视
    -0.07
    服务
    -0.07
     drying
    -0.07
    🐳
    -0.06
    国防部
    -0.06
     Dal
    -0.06
    意境
    -0.06
    POSITIVE LOGITS
    .pred
    0.08
    ٫
    0.08
    .Int
    0.07
    hev
    0.07
     eq
    0.07
    :block
    0.07
     Ю
    0.07
     œ
    0.07
    戡
    0.06
    数学
    0.06
    Act Density 0.025%

    No Known Activations