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

    Neuronpedia

    INDEX
    Explanations

    references to language and multilingualism

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

    language classifications

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ***!
    -0.51
    IBOutlet
    -0.39
     stup
    -0.35
    TestClass
    -0.35
    prepareStatement
    -0.32
     Guil
    -0.32
    MENAFN
    -0.31
     تعدى
    -0.31
     >",
    -0.31
    writeField
    -0.30
    POSITIVE LOGITS
     AssemblyCulture
    0.69
     idioma
    0.67
     lengua
    0.66
    ilingual
    0.65
     language
    0.65
     languages
    0.64
     bilingual
    0.63
     Bilingual
    0.62
     języ
    0.62
    language
    0.62
    Act Density 0.255%

    No Known Activations