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

    Neuronpedia

    INDEX
    Explanations

    bookmarking

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ad
    1.16
    är
    0.86
    .
    0.80
    In
    0.79
    లో
    0.78
    <h1>
    0.78
    But
    0.77
    2
    0.77
    什么
    0.76
    _
    0.76
    POSITIVE LOGITS
    мена
    1.07
    ди
    0.92
     vaisseaux
    0.89
     REGIUNI
    0.88
    мережа
    0.87
    extrémité
    0.86
    Bookmarks
    0.85
    که
    0.84
     ምግብ
    0.82
    ната
    0.82
    Act Density 0.001%

    No Known Activations