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

    Neuronpedia

    INDEX
    Explanations

    returning values or expressions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    um
    0.61
     Už
    0.59
     Device
    0.57
    leriyle
    0.57
     If
    0.56
     Bank
    0.55
     Web
    0.55
     Site
    0.55
    miş
    0.54
     He
    0.54
    POSITIVE LOGITS
     analiz
    0.62
     dices
    0.61
     seer
    0.60
     sobre
    0.59
     amino
    0.59
    ൽ
    0.58
     bahagian
    0.57
     tonel
    0.57
    전
    0.56
     soared
    0.55
    Act Density 0.001%

    No Known Activations