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

    Neuronpedia

    INDEX
    Explanations

    Thai language

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    間
    -0.07
     завтра
    -0.07
    rika
    -0.07
     되어
    -0.07
     дві
    -0.07
     Ker
    -0.06
    _then
    -0.06
    ("!
    -0.06
    นา
    -0.06
     "[%
    -0.06
    POSITIVE LOGITS
    removeAttr
    0.08
     тон
    0.06
     يع
    0.06
     dre
    0.06
    odash
    0.06
    ']));↵
    0.06
    :name
    0.06
     Ủy
    0.06
     Truy
    0.06
     sucks
    0.06
    Act Density 0.008%

    No Known Activations