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

    Neuronpedia

    INDEX
    Explanations

    text related to the United States, NATO, Putin and the military.

    oai_token-act-pair · gemini-2.0-flash

    military alliances

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Климат
    -0.73
    homonymie
    -0.73
    IsContent
    -0.71
    +#+#
    -0.68
    xaml
    -0.68
    帖最后由
    -0.68
    SourceChecksum
    -0.64
     }{@
    -0.63
    subpackage
    -0.63
     nahilalakip
    -0.61
    POSITIVE LOGITS
     alliance
    0.75
     allies
    0.70
     Alliance
    0.65
    alliance
    0.59
     ally
    0.58
     alliances
    0.57
    Alliance
    0.56
    spartner
    0.55
     Allies
    0.54
    odils
    0.54
    Act Density 0.912%

    No Known Activations