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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    这将
    0.73
    除了
    0.66
     Also
    0.61
    includes
    0.59
    아야
    0.58
     除
    0.57
    除
    0.57
     Dieser
    0.57
    સ્થા
    0.57
    ᑕ
    0.56
    POSITIVE LOGITS
     originalmente
    0.76
     stylistic
    0.66
     chứ
    0.66
     originally
    0.65
    本来
    0.64
     pigment
    0.63
     título
    0.63
     akin
    0.63
     kontek
    0.63
     söyl
    0.62
    Act Density 0.304%

    No Known Activations