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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ندان
    0.82
     tric
    0.74
     predisposition
    0.72
    riqu
    0.72
     rectified
    0.72
    ut
    0.71
    ng
    0.71
    ange
    0.71
    ans
    0.70
    ader
    0.70
    POSITIVE LOGITS
    어가
    0.78
    犄
    0.74
     annoy
    0.71
    truck
    0.71
    ública
    0.70
     pública
    0.68
    TEAM
    0.68
     siendo
    0.67
    어를
    0.66
    Flair
    0.66
    Act Density 0.001%

    No Known Activations