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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     co
    1.04
     chodzi
    1.02
     laut
    1.01
     somehow
    1.00
    日本では
    0.99
    em
    0.96
     गुणा
    0.96
     dire
    0.94
     ق
    0.94
     hid
    0.94
    POSITIVE LOGITS
    璺
    1.44
    情况下
    1.41
    愎
    1.40
    nson
    1.37
    <unused1155>
    1.35
    奐
    1.33
    脷
    1.32
    nA
    1.32
    漾
    1.30
    nY
    1.29
    Act Density 0.000%

    No Known Activations