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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     (
    0.89
    0.84
    á
    0.74
    it
    0.71
     been
    0.71
     dvs
    0.71
     renovations
    0.69
     also
    0.67
     includes
    0.67
     currently
    0.67
    POSITIVE LOGITS
     Алла
    0.85
     dangere
    0.83
    🌖
    0.82
     Novgorod
    0.81
     hasonló
    0.80
    Juventus
    0.79
    Frankreich
    0.79
     Eurasia
    0.77
    Belarus
    0.77
    Vlad
    0.77
    Act Density 0.002%

    No Known Activations