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

    Neuronpedia

    INDEX
    Explanations

    within you

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ur
    0.61
    '
    0.53
    is
    0.48
    anes
    0.46
    re
    0.46
    tr
    0.45
    era
    0.45
     era
    0.44
    og
    0.44
    ри
    0.44
    POSITIVE LOGITS
     Principe
    0.55
    有點
    0.53
     프린
    0.50
    恽
    0.50
    ڦ
    0.49
    戙
    0.48
    鐳
    0.47
     remarque
    0.46
    ﭜ
    0.46
    啝
    0.46
    Act Density 0.001%

    No Known Activations