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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     bolas
    1.11
    টা
    1.03
     segundos
    1.02
    бан
    0.99
    ॉयड
    0.98
     golfers
    0.97
    ه
    0.94
     segundo
    0.93
     segunda
    0.93
     pesc
    0.93
    POSITIVE LOGITS
     Despite
    1.10
    님의
    1.06
     Depending
    1.05
     Where
    1.03
    Despite
    1.00
    to
    0.99
    ⇉
    0.98
     作为
    0.98
     Neste
    0.97
     When
    0.97
    Act Density 0.000%

    No Known Activations