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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ال
    1.84
    f
    1.64
    ic
    1.53
    in
    1.44
    en
    1.31
    很多
    1.31
     une
    1.30
    a
    1.25
    el
    1.19
    or
    1.16
    POSITIVE LOGITS
     hypersurfaces
    1.41
    ט
    1.32
    鴦
    1.25
    джа
    1.23
    ంచెం
    1.21
     corticosteroids
    1.20
    ्वती
    1.20
     bolesti
    1.18
    ﺩ
    1.16
    ров
    1.15
    Act Density 0.003%

    No Known Activations