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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ssss
    0.95
     finde
    0.92
    duğ
    0.92
    sset
    0.92
     dile
    0.91
     luster
    0.89
     fik
    0.89
     అయ్య
    0.89
     bir
    0.87
     proxy
    0.87
    POSITIVE LOGITS
    予め
    0.99
    喜爱
    0.98
    基づ
    0.98
    मेंट
    0.98
     تعمل
    0.96
    កំព
    0.96
     рады
    0.93
    惮
    0.92
    欣
    0.92
    高度
    0.92
    Act Density 0.198%

    No Known Activations