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

    Neuronpedia

    INDEX
    Explanations

    God/Lord

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     God
    -1.48
    God
    -0.98
     
    -0.92
     "
    -0.89
     I
    -0.79
     god
    -0.78
     G
    -0.77
     (
    -0.77
     T
    -0.75
     Lord
    -0.75
    POSITIVE LOGITS
     Majefty
    1.62
     itſelf
    1.59
     Houſe
    1.55
     myſelf
    1.55
    ſelf
    1.54
     ―――――
    1.52
     Monfieur
    1.50
     Reſ
    1.45
     Италијани
    1.45
     Anſ
    1.43
    Act Density 0.546%

    No Known Activations