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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     castration
    1.23
    ಠ
    1.23
     occasions
    1.21
    $}
    1.18
     Zeiten
    1.17
     Thanksgiving
    1.15
    アーカイブ
    1.11
     obscured
    1.10
    $--
    1.10
     Éireann
    1.10
    POSITIVE LOGITS
    в
    1.06
    ans
    1.05
    orat
    1.01
    ем
    1.01
    ometraje
    0.99
    Batt
    0.99
    ходили
    0.98
    ミュニ
    0.98
     promove
    0.98
    ève
    0.97
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.