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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ل
    2.47
    ت
    2.33
    с
    2.08
    pte
    1.89
    没有
    1.88
    গ
    1.88
    ﮯ
    1.85
    ゅう
    1.84
     uphill
    1.81
    ro
    1.80
    POSITIVE LOGITS
     Phyl
    2.16
    م
    2.14
    ια
    2.13
    shots
    2.13
    서는
    2.06
     subscripts
    2.05
    प्तान
    2.03
    니다
    1.97
    дии
    1.96
     Проци
    1.96
    Act Density 2.705%

    No Known Activations