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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     rout
    1.33
     baš
    1.32
     ist
    1.27
     نحو
    1.27
     rameaux
    1.26
    projectName
    1.26
     টাকা
    1.26
     hinn
    1.23
     iste
    1.23
     tienes
    1.22
    POSITIVE LOGITS
    اتی
    1.24
    ⁢
    1.17
    izes
    1.06
    izing
    1.05
    uously
    1.03
    ⁤
    1.02
    identified
    0.97
    ство
    0.97
    yzed
    0.96
    ized
    0.95
    Act Density 0.000%

    No Known Activations