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

    Neuronpedia

    INDEX
    Explanations

    sudden change or event

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Utilisez
    0.64
     โรง
    0.62
     Forestry
    0.62
     防
    0.61
     編
    0.59
     danske
    0.59
     District
    0.59
     maintained
    0.59
     سمع
    0.59
    b
    0.58
    POSITIVE LOGITS
     upheaval
    1.45
     sudden
    1.34
     suddenly
    1.30
     uphe
    1.27
    突然
    1.26
     changements
    1.26
     perubahan
    1.25
     change
    1.23
     변화
    1.18
    Suddenly
    1.18
    Act Density 0.001%

    No Known Activations