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

    Neuronpedia

    INDEX
    Explanations

    Product components

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Get
    -0.07
    基金管理
    -0.07
    .START
    -0.06
     точки
    -0.06
    -div
    -0.06
     vill
    -0.06
    [href
    -0.06
    BOTTOM
    -0.06
    你以为
    -0.06
     şidd
    -0.06
    POSITIVE LOGITS
     Lazy
    0.07
     ??
    0.07
     thyroid
    0.07
    VECTOR
    0.07
    👇
    0.07
    strate
    0.07
     ابو
    0.07
    同样
    0.07
    تقليد
    0.06
     ACA
    0.06
    Act Density 0.062%

    No Known Activations