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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    with
    1.14
     überzeugt
    1.13
    vr
    1.05
    collapsed
    1.03
    ect
    1.01
    ාවිත
    0.98
    eur
    0.98
    อด
    0.98
    ﻘ
    0.97
     случаев
    0.96
    POSITIVE LOGITS
     índices
    1.15
    жение
    1.11
    应当
    1.11
     ಆದರೆ
    1.05
    шую
    1.05
     Beding
    1.03
    ари
    1.03
    icans
    1.02
    зации
    1.02
    нение
    1.01
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.