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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    5
    0.54
    .
    0.52
     buggy
    0.47
    romatic
    0.46
    ↵
    0.46
    1
    0.46
     lo
    0.45
     package
    0.44
    4
    0.44
    =
    0.43
    POSITIVE LOGITS
     તરી
    0.63
     мүмк
    0.57
    Steve
    0.49
    StarService
    0.48
     Elektrokhimiya
    0.48
     זי
    0.48
     архіви
    0.48
    ಭವ
    0.48
    髹
    0.47
    龰
    0.47
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.