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

    Neuronpedia

    INDEX
    Explanations

    technical concepts and code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    only
    0.46
     jedin
    0.39
    পল
    0.38
    oric
    0.38
    ss
    0.38
    oe
    0.37
     mistakenly
    0.36
     fatal
    0.35
     tiene
    0.34
     only
    0.34
    POSITIVE LOGITS
    ższ
    0.48
    崛起
    0.41
    ższy
    0.40
     Zu
    0.40
     새로운
    0.40
    多彩
    0.40
    Thể
    0.40
     본격
    0.40
    Tare
    0.39
    新的
    0.39
    Act Density 0.000%

    No Known Activations