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

    Neuronpedia

    INDEX
    Explanations

    resource search

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     utilisée
    0.51
    arness
    0.47
    ừa
    0.46
     assuré
    0.46
     medis
    0.46
     آتش
    0.46
    áticas
    0.45
     negativa
    0.45
     يستخدم
    0.45
     chuyện
    0.43
    POSITIVE LOGITS
     Guns
    0.41
     StreamReader
    0.41
     Geometry
    0.41
    mler
    0.40
    "],
    0.40
    shiny
    0.39
     Dime
    0.39
     напо
    0.39
    ра
    0.38
    >")
    0.38
    Act Density 0.001%

    No Known Activations