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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Computers
    0.93
     Capsules
    0.92
     ceremonies
    0.91
     capsules
    0.90
     Om
    0.86
     Cut
    0.82
     Coll
    0.82
     ○
    0.82
     jerseys
    0.82
     intercourse
    0.81
    POSITIVE LOGITS
    то
    1.05
    ть
    1.04
    ש
    1.03
    상
    1.03
    academia
    1.02
    רות
    0.98
    ב
    0.98
    v
    0.97
    Си
    0.96
    ка
    0.93
    Act Density 0.003%

    No Known Activations