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

    Neuronpedia

    INDEX
    Explanations

    references to the United States or related terms in a document

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

    us abbreviation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    keiten
    -0.39
    互联网档案馆
    -0.39
     propOrder
    -0.38
     ruban
    -0.37
     Egli
    -0.37
     Kompon
    -0.35
    באנגלית
    -0.34
    iti
    -0.33
    stdlib
    -0.33
     Bogen
    -0.33
    POSITIVE LOGITS
    eu
    0.95
    deu
    0.91
    eus
    0.91
    leu
    0.90
    teu
    0.90
    EU
    0.85
    reu
    0.83
    neur
    0.79
    eur
    0.76
     leu
    0.76
    Act Density 0.021%

    No Known Activations