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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    t
    2.17
    cially
    2.05
    ারী
    2.02
    র
    1.94
    ти
    1.87
    ার
    1.83
    yse
    1.80
     waning
    1.77
    nbsp
    1.76
    rn
    1.76
    POSITIVE LOGITS
    ći
    2.30
    ியது
    2.05
    ﻦ
    2.05
     इतना
    2.03
    い
    1.99
     merupakan
    1.98
    '.$
    1.95
    дцать
    1.89
    ۹
    1.85
    问题
    1.84
    Act Density 0.116%

    No Known Activations