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

    Neuronpedia

    INDEX
    Explanations

    Temperatures, lederhosen, tater tot

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    いる
    1.96
    માં
    1.87
    ्स
    1.69
    s
    1.60
    ﺔ
    1.54
    sers
    1.54
    ﺎ
    1.45
    servicetime
    1.45
    sing
    1.45
    ek
    1.45
    POSITIVE LOGITS
    er
    2.96
    رر
    2.79
    り
    2.45
    rrrr
    2.44
    ্সের
    2.44
    ized
    2.34
    ার
    2.34
    rrr
    2.31
    र
    2.27
    ্স
    2.25
    Act Density 0.317%

    No Known Activations