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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     NE
    0.39
     PA
    0.37
    期
    0.37
    azone
    0.35
    Nexus
    0.35
     GR
    0.35
    ，
    0.35
    豔
    0.34
     Nexus
    0.34
    softmax
    0.34
    POSITIVE LOGITS
    ুদ্ধে
    0.41
    ців
    0.39
    obuf
    0.39
    yyyyyyyy
    0.38
    cherichia
    0.37
    ຄວ
    0.36
    بحث
    0.36
    闶
    0.36
     oversee
    0.36
     اوس
    0.36
    Act Density 0.000%

    No Known Activations