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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    рная
    1.13
     празд
    1.11
     ﺍﻟ
    1.11
     железнодоро
    1.10
     vivió
    1.09
    рные
    1.07
     fácilmente
    1.06
    рной
    1.05
     necesaria
    1.04
     períodos
    1.04
    POSITIVE LOGITS
    s
    1.18
     to
    0.96
    en
    0.91
    Lo
    0.91
    hi
    0.90
    or
    0.90
    с
    0.89
    %
    0.88
    5
    0.86
    )
    0.84
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.