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

    Neuronpedia

    INDEX
    Explanations

    content type json

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    oeste
    1.07
    anel
    1.06
     fenó
    1.06
     алюми
    1.05
     senin
    1.04
     Phen
    1.03
    ळी
    1.01
     الزمن
    1.01
     fontes
    1.00
    ので
    0.98
    POSITIVE LOGITS
    ς
    1.17
    ٰ
    1.05
    مة
    1.03
    нуться
    1.02
    اتي
    0.99
    musical
    0.98
    ционных
    0.97
    namen
    0.97
    lays
    0.97
    ইতি
    0.95
    Act Density 0.001%

    No Known Activations