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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    n
    0.57
    ры
    0.53
    整个
    0.52
    ক
    0.50
    en
    0.48
    st
    0.48
    其他
    0.48
    été
    0.47
    lı
    0.46
    相比
    0.46
    POSITIVE LOGITS
     Inspired
    0.48
     Ugar
    0.47
    یدار
    0.46
     Nemat
    0.46
     renderEncoder
    0.46
    馍
    0.45
     Sound
    0.45
     Publish
    0.45
    밈
    0.45
     Navigator
    0.45
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.