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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ش
    0.63
    casting
    0.56
     ඔබට
    0.55
    کرو
    0.54
    ور
    0.54
    TOR
    0.52
    ﻧ
    0.52
     dépens
    0.51
    ifrån
    0.51
     postérieure
    0.51
    POSITIVE LOGITS
    ный
    0.80
    ная
    0.70
    它
    0.67
     hugely
    0.64
    ន៍
    0.64
    ные
    0.63
     While
    0.62
    身边
    0.61
    кий
    0.60
    ة
    0.58
    Act Density 0.002%

    No Known Activations