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

    Neuronpedia

    INDEX
    Explanations

    comfortable words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     metaphors
    0.42
     ไฟ
    0.38
     eten
    0.38
     roh
    0.38
     estruturas
    0.37
     digraph
    0.37
     cookieParser
    0.37
     estructuras
    0.37
     Meals
    0.37
     spécifiques
    0.37
    POSITIVE LOGITS
    困
    0.46
    adis
    0.45
    ebook
    0.45
     निश्च
    0.44
    giène
    0.44
    page
    0.43
    propion
    0.41
    tenth
    0.41
     बुक
    0.41
    页面
    0.41
    Act Density 0.003%

    No Known Activations