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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Einsatz
    0.42
    ဩ
    0.40
     Miłos
    0.40
     infert
    0.39
    ကောင်း
    0.39
     Tired
    0.39
    籀
    0.38
     appalled
    0.38
    🍾
    0.38
     رہتے
    0.37
    POSITIVE LOGITS
    ти
    0.44
    ue
    0.43
    ifle
    0.43
    nge
    0.42
     του
    0.42
     (
    0.41
    IMENT
    0.41
    iffany
    0.41
     функции
    0.41
     של
    0.41
    Act Density 0.008%

    No Known Activations