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

    Neuronpedia

    INDEX
    Explanations

    adapt, frustration, advantageous

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     }{
    0.48
    наче
    0.46
    shopping
    0.45
    c
    0.45
    tac
    0.44
    v
    0.43
    ":
    0.43
    trip
    0.43
    tact
    0.42
    란드
    0.42
    POSITIVE LOGITS
     мм
    0.55
    шек
    0.47
    昙
    0.46
     hubs
    0.45
     biedt
    0.45
     dañ
    0.45
    一系列
    0.45
     aynı
    0.44
    时间内
    0.44
    அல்ல
    0.44
    Act Density 0.002%

    No Known Activations