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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ے
    1.26
    nim
    1.09
     ราย
    1.06
    ানে
    1.05
     infrequently
    1.05
    ють
    1.03
    legal
    1.02
     jantung
    1.01
    ﻲ
    1.00
    ﺎ
    1.00
    POSITIVE LOGITS
     thrones
    1.06
    𝘞
    1.00
    вропей
    0.99
     opposites
    0.95
     tirar
    0.93
    览
    0.93
    会将
    0.92
    ه‌های
    0.92
     chromosphere
    0.92
    )}^
    0.91
    Act Density 0.004%

    No Known Activations