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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     particular
    0.52
     особы
    0.48
     starken
    0.48
     ő
    0.47
    ினும்
    0.46
     Werke
    0.46
    aunque
    0.45
    ዞ
    0.44
    ي
    0.44
    διο
    0.44
    POSITIVE LOGITS
    ISTIC
    0.46
    裾
    0.45
    負荷
    0.42
    ਣ
    0.42
    리스
    0.41
    defining
    0.41
     Dyke
    0.40
     Peas
    0.40
    ICreate
    0.40
    렉
    0.39
    Act Density 0.000%

    No Known Activations