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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Modell
    0.82
     pejabat
    0.77
     Radiology
    0.76
    erkraut
    0.72
     Model
    0.71
     chiffres
    0.71
     Ergebn
    0.71
     catatan
    0.70
     Gesamt
    0.69
     ш
    0.68
    POSITIVE LOGITS
     위의
    0.80
     overflowing
    0.72
    ミング
    0.71
    ación
    0.69
     opposites
    0.68
     from
    0.68
    说是
    0.67
     above
    0.65
     below
    0.65
    ंकडून
    0.65
    Act Density 0.000%

    No Known Activations