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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    лі
    0.77
    не
    0.76
     м
    0.76
    ээ
    0.75
    ід
    0.73
    Д
    0.71
    ці
    0.70
    এ
    0.70
    ки
    0.70
    кови
    0.70
    POSITIVE LOGITS
     восприя
    0.82
     eyebrows
    0.79
    얗
    0.79
     psyche
    0.78
     destinés
    0.78
    িয়াছিলেন
    0.77
     Preise
    0.77
     seating
    0.76
     direttamente
    0.76
     wrists
    0.74
    Act Density 0.387%

    No Known Activations