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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     esim
    0.86
    katore
    0.85
    papier
    0.84
    profession
    0.83
    nour
    0.82
    tre
    0.81
    des
    0.80
    لف
    0.80
    Segmentation
    0.79
    nobyl
    0.79
    POSITIVE LOGITS
    ah
    0.98
     воспользова
    0.98
    á
    0.91
    에
    0.90
    >*</
    0.89
    ov
    0.88
    iping
    0.87
    arial
    0.85
    am
    0.84
    ahah
    0.83
    Act Density 0.001%

    No Known Activations