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

    Neuronpedia

    INDEX
    Explanations

    code characters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     inference
    -0.08
     dá
    -0.07
     PURPOSE
    -0.07
    .jpeg
    -0.07
    .navigationController
    -0.07
     Chance
    -0.06
    HomeController
    -0.06
    (Content
    -0.06
    为了
    -0.06
     antivirus
    -0.06
    POSITIVE LOGITS
    ุตสาห
    0.07
    desk
    0.07
    شب
    0.06
    )\<
    0.06
     відмов
    0.06
    пор
    0.06
    mir
    0.06
     tournaments
    0.06
     srv
    0.06
    std
    0.06
    Act Density 0.046%

    No Known Activations