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

    Neuronpedia

    INDEX
    Explanations

    lists, numbers, or technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    uvwxyz
    0.42
     daisies
    0.42
    WithOwner
    0.41
    dale
    0.40
     opal
    0.39
     baking
    0.39
    oggle
    0.38
    mills
    0.38
    Walls
    0.38
     hiking
    0.38
    POSITIVE LOGITS
     संदेश
    0.42
    实施
    0.40
    身影
    0.38
     처음
    0.37
     참여
    0.36
     Hồng
    0.36
     ncol
    0.35
     ابھی
    0.35
     kiến
    0.34
     전문
    0.34
    Act Density 0.000%

    No Known Activations