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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    Passenger
    0.41
    졀
    0.41
     passenger
    0.39
     Passenger
    0.38
    वळ
    0.38
    Simpl
    0.37
    各
    0.37
    سک
    0.37
     Ease
    0.37
    YH
    0.36
    POSITIVE LOGITS
     терми
    0.44
     termes
    0.43
     filtre
    0.43
    ędzie
    0.43
     уены
    0.41
    ѓ
    0.41
     플레이
    0.40
     spelt
    0.40
     لعب
    0.39
     spielt
    0.39
    Act Density 0.002%

    No Known Activations