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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    자는
    -0.08
    옥
    -0.07
    _odd
    -0.07
    מדינ
    -0.07
     uğ
    -0.07
    建设
    -0.07
    localctx
    -0.07
    สว
    -0.06
    氕
    -0.06
    testimonial
    -0.06
    POSITIVE LOGITS
    (of
    0.09
     Payload
    0.07
    haul
    0.07
     compromised
    0.07
     Erotic
    0.07
    组装
    0.07
     Mobility
    0.07
    香蕉
    0.07
    handlers
    0.07
     TEMPLATE
    0.07
    Act Density 0.356%

    No Known Activations