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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     recap
    0.45
     questões
    0.43
     ![
    0.42
     Bél
    0.42
    𒄩
    0.42
    救援
    0.41
    殯
    0.41
     ሽፋን
    0.40
    鈁
    0.40
    роят
    0.40
    POSITIVE LOGITS
    nc
    0.46
    Trans
    0.46
     trans
    0.45
     Trans
    0.44
    dummy
    0.43
    Wheel
    0.43
    p
    0.42
    Vers
    0.42
    i
    0.41
    as
    0.41
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.