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

    Neuronpedia

    INDEX
    Explanations

    references to American entities or concepts

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

    Following the word "American"

    np_acts-logits-general · gemini-2.0-flash

    American or USA

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nahilalakip
    -0.89
     فريبيس
    -0.87
    ništ
    -0.78
    SPJ
    -0.77
     mxArray
    -0.75
    authToken
    -0.73
    ]")]
    -0.72
    rhosis
    -0.72
    oriasis
    -0.72
    SBATCH
    -0.71
    POSITIVE LOGITS
    American
    0.89
     américain
    0.87
    Amer
    0.86
     americana
    0.82
     Amerika
    0.82
    USA
    0.82
     Serikat
    0.81
    Amerika
    0.80
    🇺🇸
    0.80
    ized
    0.79
    Act Density 0.179%

    No Known Activations