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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    rique
    1.15
    hibited
    1.01
    hibition
    1.01
    liqu
    0.98
    ്രീ
    0.98
    ppies
    0.97
    drawable
    0.97
     bogey
    0.96
    tan
    0.96
    volve
    0.95
    POSITIVE LOGITS
    л
    1.34
     diarias
    1.30
    з
    1.29
     ৯০
    1.23
    相關
    1.20
    тся
    1.20
     neues
    1.20
     toepassing
    1.19
    鏘
    1.18
    эт
    1.16
    Act Density 0.000%

    No Known Activations