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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     uche
    -0.08
     genu
    -0.08
     claramente
    -0.08
     evidente
    -0.08
     aparent
    -0.07
     Challenge
    -0.07
     imped
    -0.07
     unim
    -0.07
     фун
    -0.07
     panjang
    -0.07
    POSITIVE LOGITS
     notify
    0.10
     veranderingen
    0.09
    notify
    0.09
     notification
    0.09
    变化
    0.09
    (keyword
    0.08
     собы
    0.08
     nouveautés
    0.08
    (notification
    0.08
     wishlist
    0.08
    Act Density 0.032%

    No Known Activations