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

    Neuronpedia

    INDEX
    Explanations

    foreign words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    @Json
    -0.07
     aquatic
    -0.07
    elan
    -0.07
    ☤
    -0.07
    Abs
    -0.07
    toBe
    -0.07
     dış
    -0.07
    .lastname
    -0.07
     userDao
    -0.07
    赖以
    -0.07
    POSITIVE LOGITS
     międzynarod
    0.08
    wd
    0.08
    中国人民
    0.08
    בע
    0.07
    пу
    0.07
     депутат
    0.07
    人民政府
    0.07
     borrowers
    0.07
     impartial
    0.07
    станавлива
    0.07
    Act Density 0.002%

    No Known Activations