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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    -
    1.51
    \
    1.37
    )
    1.33
    ;
    1.23
     y
    1.22
     v
    1.21
    }
    1.21
     d
    1.20
     n
    1.16
     r
    1.15
    POSITIVE LOGITS
    گ
    1.42
    ن
    1.40
    ut
    1.30
    ع
    1.30
    ای
    1.25
    يا
    1.22
    چ
    1.20
    З
    1.20
    ה
    1.19
    বি
    1.15
    Act Density 0.000%

    No Known Activations