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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    别人的
    1.19
    另一种
    1.12
     المنا
    1.11
     какого
    1.07
     ideological
    1.02
    别人
    1.01
     другого
    1.00
     qualunque
    0.99
    正确的
    0.99
    ﻣ
    0.99
    POSITIVE LOGITS
     barely
    1.08
    lare
    1.03
    arend
    1.02
    arla
    1.00
    lada
    0.99
    ေ
    0.97
    agascar
    0.96
     半袖
    0.96
     departs
    0.95
     culminates
    0.94
    Act Density 0.109%

    No Known Activations