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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     إس
    0.86
    regen
    0.78
    GI
    0.77
    リア
    0.75
    世話
    0.73
    çi
    0.72
     sara
    0.71
    యర్
    0.71
     Мар
    0.70
    WUE
    0.70
    POSITIVE LOGITS
     Ф
    0.94
     F
    0.90
    Desde
    0.86
     FROM
    0.84
     Fl
    0.80
     hooks
    0.78
    Freel
    0.77
     Nested
    0.77
     Fans
    0.77
    F
    0.77
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.