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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Campe
    0.45
    ແມ
    0.43
    λος
    0.40
    meyi
    0.40
    ПУ
    0.40
     πά
    0.39
     نيك
    0.39
    ⇐
    0.39
     sunlight
    0.38
     Infect
    0.37
    POSITIVE LOGITS
     plen
    0.39
     ful
    0.39
    Morning
    0.38
     التن
    0.36
     internalization
    0.36
    Ful
    0.35
     skór
    0.35
     朝
    0.34
    hw
    0.34
     Veg
    0.34
    Act Density 0.000%

    No Known Activations