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

    Neuronpedia

    INDEX
    Explanations

    references to military honors and awards

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Awards, honors, and military decorations

    np_acts-logits-general · gemini-2.0-flash

    medals and orders

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    RoutingModule
    -0.46
    amblea
    -0.41
    pasto
    -0.39
    siel
    -0.39
    rosin
    -0.38
     furnish
    -0.38
     esternos
    -0.38
    GeneratedCode
    -0.37
    الحياه
    -0.37
    inex
    -0.37
    POSITIVE LOGITS
     honorary
    1.00
     Order
    0.91
     Medal
    0.90
     posthum
    0.90
     honour
    0.89
     honor
    0.88
     Honorary
    0.86
     recognition
    0.86
    Honorary
    0.85
     Honour
    0.85
    Act Density 0.147%

    No Known Activations