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

    Neuronpedia

    INDEX
    Explanations

    _________________________

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    鹑
    1.07
    བ་
    0.96
    ಸ್‌
    0.95
    ರ್ಚ
    0.93
    Outstanding
    0.92
     পরই
    0.91
    懋
    0.90
    もちろん
    0.89
    ούν
    0.88
     disponibilités
    0.88
    POSITIVE LOGITS
    aline
    0.98
    clearInterval
    0.96
     heap
    0.95
    blackjack
    0.94
    aan
    0.93
    _,
    0.92
     checklist
    0.91
    nY
    0.91
    มือ
    0.90
    kk
    0.90
    Act Density 0.006%

    No Known Activations