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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ?”
    0.47
     l
    0.45
     kwe
    0.45
     æ
    0.45
     ceva
    0.44
     pamo
    0.44
     H
    0.44
     berp
    0.44
    ):
    0.43
    dou
    0.43
    POSITIVE LOGITS
    轸
    0.42
    两种
    0.42
    Typography
    0.39
    хозяй
    0.38
     Whiting
    0.38
     Perimeter
    0.38
    라서
    0.38
     Translations
    0.38
    bagai
    0.38
    销
    0.37
    Act Density 0.000%

    No Known Activations