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

    Neuronpedia

    INDEX
    Explanations

    proper nouns of countries and people involved in national politics and security.

    oai_token-act-pair · gemini-2.0-flash

    US, States

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ↵↵
    -0.49
    ↵
    -0.47
     random
    -0.44
    -0.44
    分
    -0.43
    感
    -0.43
    Random
    -0.42
     κά
    -0.42
     T
    -0.42
     fa
    -0.42
    POSITIVE LOGITS
    脚注の使い方
    1.05
    yntaxException
    1.02
    исленность
    0.95
     дописавши
    0.94
    verwijspagina
    0.93
    IsMutable
    0.91
     '\\;'
    0.87
     disambiguazione
    0.87
    expandindo
    0.86
    ंदीखरीदारी
    0.85
    Act Density 10.628%
    No Known Activations