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

    Neuronpedia

    INDEX
    Explanations

    movies and plots

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ros
    0.56
    ar
    0.50
    ’
    0.48
    s
    0.47
    io
    0.46
    field
    0.46
    ives
    0.44
    '
    0.44
    file
    0.43
    en
    0.43
    POSITIVE LOGITS
     філь
    0.53
     уби
    0.51
     цього
    0.50
     фено
    0.49
     ו
    0.49
     задачи
    0.48
     найбіль
    0.48
     মহারাজ
    0.48
     nhất
    0.48
     сюжет
    0.47
    Act Density 0.010%

    No Known Activations