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

    Neuronpedia

    INDEX
    Explanations

    numpy as / right now as

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Forth
    0.73
     working
    0.64
     ker
    0.63
    Ker
    0.61
    cubic
    0.60
    Са
    0.59
     day
    0.59
    working
    0.58
     Ker
    0.57
    酒
    0.57
    POSITIVE LOGITS
     ಡಿ
    0.66
    ਏ
    0.60
    赊
    0.58
     distributing
    0.56
    ಂಚ
    0.55
     trộn
    0.55
    恰
    0.54
     ගත
    0.54
     nồi
    0.53
    ArchiveAction
    0.53
    Act Density 0.042%

    No Known Activations