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

    Neuronpedia

    INDEX
    Explanations

    Spanish "puedo" "está" Italian "arrivo"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     featured
    0.86
     factor
    0.84
     nanof
    0.79
    化的
    0.79
     blockchain
    0.78
    يكية
    0.78
     deton
    0.78
     quan
    0.77
     featuring
    0.76
     sensor
    0.75
    POSITIVE LOGITS
    ছেন
    1.51
    śmy
    1.37
    тся
    1.25
    ים
    1.19
    লেন
    1.13
    ছিলেন
    1.12
    েন
    1.11
     सकता
    1.09
    ται
    1.07
    ছি
    1.07
    Act Density 0.186%

    No Known Activations