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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    OBJ
    0.41
    Ro
    0.39
     заинтересо
    0.39
    ろし
    0.38
    (",")
    0.38
    nicheskij
    0.38
    roffen
    0.37
    iterranée
    0.37
    зі
    0.37
     孔
    0.37
    POSITIVE LOGITS
     mutat
    0.40
    서트
    0.39
     acum
    0.37
     Crou
    0.36
     muit
    0.36
     क
    0.36
     Toto
    0.36
     belong
    0.35
     Enum
    0.35
     protecting
    0.35
    Act Density 0.000%

    No Known Activations