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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    Ꮈ
    0.43
     разме
    0.42
    気になる
    0.42
    комиться
    0.41
    选题
    0.40
    이지만
    0.40
     sozinho
    0.40
     भर्ती
    0.39
     temper
    0.38
    ൻ
    0.38
    POSITIVE LOGITS
     Styles
    0.44
    systems
    0.42
     SUPPORT
    0.42
    support
    0.42
     FISH
    0.41
     Support
    0.40
    weds
    0.40
     دعم
    0.40
     Wedding
    0.39
     Fischer
    0.39
    Act Density 0.001%

    No Known Activations