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

    Neuronpedia

    INDEX
    Explanations

    strong brewed

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    redit
    0.40
     credit
    0.39
     deswegen
    0.38
     subordin
    0.38
    colorize
    0.38
     कंटे
    0.38
    មី
    0.38
    そのため
    0.37
     цвета
    0.37
     wegen
    0.37
    POSITIVE LOGITS
    вший
    0.40
     الرا
    0.37
    اسية
    0.37
     queridos
    0.36
    űkö
    0.36
    也有
    0.35
    倝
    0.35
    accro
    0.34
     etmiş
    0.34
    িত্তিক
    0.33
    Act Density 0.000%

    No Known Activations