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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     slipped
    0.82
     accession
    0.80
     crumpled
    0.80
     roared
    0.79
     prevailed
    0.79
     sharply
    0.78
     grilled
    0.77
     ascribed
    0.77
     entrusted
    0.76
     tucked
    0.75
    POSITIVE LOGITS
     متجه
    0.79
    硏
    0.77
    الم
    0.77
     شدن
    0.76
     بي
    0.75
    ق
    0.74
    ال
    0.74
     الرياضيات
    0.73
    ক
    0.73
    電池
    0.71
    Act Density 0.000%

    No Known Activations