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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     as
    1.20
     or
    1.20
        
    1.12
    ﺍ
    1.06
     s
    1.05
     t
    1.01
    ↵
    1.00
     V
    0.98
     I
    0.96
    -
    0.96
    POSITIVE LOGITS
    ين
    1.20
    ام
    1.18
    ၅
    1.11
    ق
    1.08
    もら
    1.07
    in
    1.05
    ни
    1.04
    ح
    1.03
    ли
    1.02
    كان
    1.02
    Act Density 0.000%

    No Known Activations