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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    лед
    0.73
    schedule
    0.70
    ບັນ
    0.70
    주
    0.70
    éclair
    0.69
    від
    0.66
    othérapie
    0.64
    $
    0.63
    thebibliography
    0.63
    application
    0.63
    POSITIVE LOGITS
     Anda
    0.74
     vicino
    0.73
     Straße
    0.71
     sighed
    0.70
     scolded
    0.69
    做得
    0.69
     сосед
    0.68
     Selain
    0.67
     slags
    0.67
     Volks
    0.66
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.