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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Dun
    0.79
     Shaw
    0.77
    Dun
    0.77
     Shay
    0.72
    Shaw
    0.71
     Ilana
    0.70
     Els
    0.70
     Elementary
    0.70
    学
    0.70
     Study
    0.69
    POSITIVE LOGITS
    agency
    0.98
    Agency
    0.90
     CCM
    0.90
    immung
    0.88
    ico
    0.88
    гент
    0.88
     Cardoso
    0.88
     agen
    0.87
     portuguesa
    0.87
     Widodo
    0.87
    Act Density 2.983%

    No Known Activations