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

    Neuronpedia

    INDEX
    Explanations

    words related to religion, especially angels, plus other words that might be errors, or vaguely related to spirituality

    oai_token-act-pair · gemini-2.0-flash

    connections, angels

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Polity
    -1.17
    IUrlHelper
    -1.04
     resourceCulture
    -1.03
    StoryboardSegue
    -0.98
     Vapour
    -0.95
    InjectAttribute
    -0.94
     podjela
    -0.93
     ***!
    -0.93
     transfieras
    -0.91
     auroit
    -0.90
    POSITIVE LOGITS
     The
    0.79
     
    0.73
     and
    0.71
     But
    0.71
     P
    0.71
     In
    0.69
     "
    0.68
     $
    0.67
     A
    0.66
     R
    0.65
    Act Density 0.798%

    No Known Activations