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

    Neuronpedia

    INDEX
    Explanations

    multiple languages

    np_max-act · gemini-2.0-flash

    This neuron activates on tokens containing non-ASCII or accented characters, i.e. foreign-language words.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     excell
    -0.07
     Equity
    -0.07
     यद
    -0.07
    kaz
    -0.07
     speaks
    -0.07
    -cert
    -0.06
    "Our
    -0.06
    18
    -0.06
    LANGUAGE
    -0.06
    для
    -0.06
    POSITIVE LOGITS
    ('{}
    0.06
    열
    0.06
     링크
    0.06
     Utf
    0.06
    .em
    0.06
     Mehmet
    0.06
    _W
    0.06
     taj
    0.06
     BUFF
    0.06
     whim
    0.06
    Act Density 0.169%

    No Known Activations