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

    Neuronpedia

    INDEX
    Explanations

    non-English text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ภัย
    -0.07
    ırı
    -0.07
    ARING
    -0.07
     عليها
    -0.07
    reports
    -0.07
    .def
    -0.07
    965
    -0.07
    popup
    -0.07
    .fore
    -0.07
     lateinit
    -0.07
    POSITIVE LOGITS
    hi
    0.08
     discriminator
    0.08
     duk
    0.08
    erezh
    0.07
     kru
    0.07
    igitte
    0.07
    ход
    0.07
    oh
    0.07
    duk
    0.07
    ose
    0.07
    Act Density 0.001%

    No Known Activations