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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ду
    1.22
    чала
    1.21
    ت
    1.20
    سازی
    1.16
    tım
    1.14
    dote
    1.13
     алфа
    1.09
    woman
    1.09
    若
    1.08
    stations
    1.08
    POSITIVE LOGITS
     tortured
    1.12
     umbrellas
    1.12
    個セット
    1.04
     buttons
    1.01
     perfectly
    0.99
    ്ലാ
    0.98
     suddenly
    0.97
     condenser
    0.96
     helmets
    0.94
     الاي
    0.94
    Act Density 0.000%

    No Known Activations