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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ה
    1.13
    িব
    1.11
    ń
    1.04
    الح
    1.01
    ான
    1.01
    ாக
    0.99
    VARIABLE
    0.99
    と思います
    0.96
     constater
    0.94
     спро
    0.94
    POSITIVE LOGITS
    ﺏ
    1.44
    ﻕ
    1.35
    ၎င်း
    1.33
    ﻙ
    1.27
    탄소년
    1.21
    nymi
    1.20
     Mourinho
    1.20
    askell
    1.20
    race
    1.18
    ﺕ
    1.17
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.