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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ক
    0.54
     andDevice
    0.52
    ope
    0.51
    ile
    0.50
    ق
    0.50
     jonka
    0.49
     is
    0.49
    ب
    0.48
    icht
    0.48
     vuonna
    0.48
    POSITIVE LOGITS
    вей
    0.53
    ман
    0.52
    вна
    0.50
     आवश्यक
    0.50
     sabot
    0.48
    ινε
    0.48
    raciones
    0.48
     benöt
    0.47
    utables
    0.47
    восто
    0.47
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.