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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ’
    0.85
    শীল
    0.84
    abod
    0.81
    나
    0.81
    א
    0.80
    า
    0.80
    ان
    0.78
    mare
    0.77
    th
    0.75
    ucker
    0.75
    POSITIVE LOGITS
     undermines
    1.15
     uygulan
    1.09
     nogen
    1.02
     относится
    1.00
     deles
    1.00
     noen
    0.97
     provinsi
    0.96
     melibatkan
    0.95
    ﻈ
    0.95
     kişi
    0.94
    Act Density 0.000%

    No Known Activations