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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     klart
    1.28
     Scotts
    1.14
     hasil
    1.12
    чени
    1.09
     Gladi
    1.02
     tussen
    1.01
    rasekhar
    1.01
     pleno
    1.00
    izens
    0.99
    ηση
    0.99
    POSITIVE LOGITS
    بد
    1.29
    䣬
    1.25
    ל
    1.18
    ب
    1.16
     ঘুষ
    1.13
    로
    1.13
    ات
    1.10
    اته
    1.09
    نګ
    1.09
    푸
    1.08
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.