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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     closure
    0.47
    .
    0.45
    ре
    0.43
     violence
    0.42
     change
    0.42
     limitation
    0.42
    p
    0.42
     surrogate
    0.42
    зи
    0.41
     spongy
    0.41
    POSITIVE LOGITS
     подготовлено
    0.56
     presentado
    0.54
     Pixar
    0.53
     miembro
    0.51
    𝟎
    0.51
     مجموعة
    0.50
     முன்னணி
    0.50
     modelos
    0.50
    ت
    0.50
     किड्स
    0.48
    Act Density 0.010%

    No Known Activations