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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ografija
    -0.58
    Contactez
    -0.57
    Identyfik
    -0.54
    esercito
    -0.53
    Personendaten
    -0.53
     ilang
    -0.52
    Géographie
    -0.52
     seldom
    -0.50
     sleeps
    -0.50
    ]').
    -0.50
    POSITIVE LOGITS
     المعيارى
    0.56
    0.49
     using
    0.48
    发表于
    0.46
     developing
    0.46
    using
    0.45
     تضيفلها
    0.45
    ,
    0.45
     producing
    0.45
     use
    0.45
    Act Density 0.002%

    No Known Activations