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

    Neuronpedia

    INDEX
    Explanations

    standard library

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     even
    0.36
     shut
    0.32
     expon
    0.31
     même
    0.30
     gn
    0.30
     accustomed
    0.29
     might
    0.29
     abyss
    0.28
     speck
    0.28
     nes
    0.28
    POSITIVE LOGITS
    টি
    0.30
     दीपा
    0.28
    halloween
    0.28
    `${
    0.28
    測試
    0.27
    Máy
    0.27
    ழிவு
    0.26
     दिवाली
    0.26
    均为
    0.26
    السلام
    0.25
    Act Density 0.000%

    No Known Activations