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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     +
    0.67
    like
    0.67
     be
    0.64
     nonzero
    0.64
    b
    0.64
    א
    0.64
    f
    0.61
    og
    0.59
     $
    0.58
     any
    0.58
    POSITIVE LOGITS
     conocimientos
    0.78
     conocer
    0.77
     FODC
    0.77
    养成
    0.75
     conhecimentos
    0.75
     разобраться
    0.74
     profesionales
    0.73
     पहु
    0.73
    伡
    0.73
     caseworker
    0.72
    Act Density 0.000%

    No Known Activations