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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ט
    0.59
    ен
    0.57
    ту
    0.55
    ต์
    0.52
    ну
    0.52
    티브
    0.51
    াজি
    0.51
    жене
    0.51
    тиву
    0.51
    ሖ
    0.50
    POSITIVE LOGITS
     in
    0.71
     l
    0.66
     i
    0.66
     d
    0.63
     s
    0.62
     not
    0.61
     et
    0.60
     es
    0.59
     more
    0.58
     la
    0.57
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.