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

    Neuronpedia

    INDEX
    Explanations

    app.use(

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ړه
    0.47
    딨
    0.44
     Fleurit
    0.42
    न्देल
    0.40
    PositionY
    0.40
    สัตว์
    0.40
    蕪
    0.39
    돛
    0.39
    क्षत्र
    0.39
     Chauhan
    0.39
    POSITIVE LOGITS
     '/',
    0.70
    ('/
    0.68
     '/
    0.67
    ('/',
    0.65
     bodyParser
    0.62
     express
    0.61
    bodyParser
    0.61
     "/",
    0.59
    express
    0.57
     cookieParser
    0.55
    Act Density 0.002%

    No Known Activations