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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    IN
    1.11
    ン
    1.02
    न
    0.98
     américains
    0.98
    OL
    0.96
    াস
    0.95
    ран
    0.95
    IPV
    0.95
    DC
    0.93
    لق
    0.92
    POSITIVE LOGITS
    ת
    1.38
     ו
    1.19
     and
    1.17
    ü
    1.03
     и
    1.02
    써
    0.98
     و
    0.97
    人和
    0.96
    то
    0.92
    ер
    0.92
    Act Density 0.000%

    No Known Activations