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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    蜼
    0.54
    👜
    0.52
     يوم
    0.50
    wijs
    0.48
    隐私
    0.48
    કરી
    0.48
    ють
    0.47
    ovirus
    0.47
     commencent
    0.47
    दर्
    0.46
    POSITIVE LOGITS
    Plate
    0.52
    u
    0.48
    Birmingham
    0.48
    .
    0.48
    Corner
    0.46
    Single
    0.46
    0
    0.46
    on
    0.46
     بود
    0.46
     آ
    0.45
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.