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

    Neuronpedia

    INDEX
    Explanations

    colors

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dispositivos
    -0.08
    完善
    -0.08
     Offline
    -0.08
     Constraints
    -0.08
     Written
    -0.08
     intime
    -0.08
    秘书
    -0.08
     Employment
    -0.07
     Restrictions
    -0.07
     Parking
    -0.07
    POSITIVE LOGITS
     colors
    0.25
     રંગ
    0.25
     रंग
    0.25
    颜色
    0.25
     цвета
    0.23
     رنگ
    0.23
    Color
    0.23
    色
    0.22
     couleurs
    0.22
     colores
    0.22
    Act Density 0.427%

    No Known Activations