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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    惆
    1.06
     Phần
    1.04
     शुरू
    1.00
    情况
    0.98
    മ
    0.98
     गुर्जर
    0.97
    tf
    0.97
     Kiến
    0.94
    捭
    0.94
     Página
    0.93
    POSITIVE LOGITS
     by
    1.29
    at
    1.25
    ל
    1.21
     been
    1.20
    in
    1.16
    an
    1.13
    al
    1.10
    ong
    1.09
    л
    1.09
    ل
    1.09
    Act Density 0.000%

    No Known Activations