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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     given
    0.74
    given
    0.71
    上記
    0.66
    ઃ
    0.66
     above
    0.64
     выше
    0.63
    following
    0.63
    indicated
    0.63
    above
    0.62
    给定
    0.61
    POSITIVE LOGITS
     Choice
    0.77
     Choices
    0.76
    Choice
    0.65
     choices
    0.61
     écran
    0.60
     বুঝি
    0.60
     Things
    0.58
     Lawrence
    0.58
     Od
    0.57
     Items
    0.57
    Act Density 0.000%

    No Known Activations