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

    Neuronpedia

    INDEX
    Explanations

    game choices and strategy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ó
    0.54
    ew
    0.52
    hews
    0.52
    ta
    0.50
    encent
    0.50
    emon
    0.49
     übers
    0.49
    daa
    0.48
    aisen
    0.48
     ì
    0.48
    POSITIVE LOGITS
     keterampilan
    0.47
    وها
    0.45
    र
    0.42
    钙
    0.40
    颌
    0.40
     buccal
    0.40
    绊
    0.40
    乐趣
    0.40
     культура
    0.40
    धित
    0.39
    Act Density 0.001%

    No Known Activations