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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     содержи
    0.83
     рэгістра
    0.83
     сторо
    0.82
     стаў
    0.81
     должны
    0.80
     estampado
    0.79
     начали
    0.79
    ковь
    0.79
     احتم
    0.78
     Pamplona
    0.78
    POSITIVE LOGITS
    ating
    0.68
    6
    0.67
    ing
    0.64
     broker
    0.64
    Lecture
    0.64
    <0xD0>
    0.63
    Gold
    0.63
     Lecture
    0.63
    >>();
    0.63
     blower
    0.63
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.