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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Hours
    0.85
     shades
    0.82
     hours
    0.78
     spines
    0.78
     видов
    0.75
     garlands
    0.74
     adjustments
    0.73
     affective
    0.71
    Hours
    0.71
    gaard
    0.70
    POSITIVE LOGITS
     актриса
    0.71
    谔
    0.70
    ровала
    0.69
    ам
    0.68
    ровали
    0.68
    ccionar
    0.68
    твор
    0.68
    amse
    0.67
    テンツ
    0.66
     डाइजेस्टिव
    0.65
    Act Density 0.000%

    No Known Activations