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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    【
    0.40
    Od
    0.39
    Если
    0.39
     Tender
    0.38
    琬
    0.38
    eteer
    0.37
     faveur
    0.37
    I
    0.37
    Issue
    0.37
    Occ
    0.37
    POSITIVE LOGITS
    тьми
    0.42
    зить
    0.41
    }^{*}=\
    0.40
    週間
    0.40
     середи
    0.38
    الات
    0.38
    зя
    0.37
     दैनिक
    0.37
    кугӀ
    0.37
    ertos
    0.37
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.