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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     a
    0.92
     dosage
    0.86
     agile
    0.84
     معد
    0.78
     за
    0.78
     the
    0.77
    out
    0.77
     под
    0.77
    0.76
     -
    0.76
    POSITIVE LOGITS
    esque
    1.51
    పురం
    1.31
    Universität
    1.25
    대학교
    1.21
    ianSpace
    1.20
     Adası
    1.19
     Üniversitesi
    1.18
     Cruises
    1.17
     Medal
    1.16
     Brewery
    1.14
    Act Density 0.777%

    No Known Activations