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

    Neuronpedia

    INDEX
    Explanations

    words starting with pre

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    a
    1.26
    "
    1.22
    '
    1.08
    ા
    1.08
    c
    1.01
    לי
    0.98
    া
    0.96
    ス
    0.90
    ון
    0.89
    く
    0.88
    POSITIVE LOGITS
    ors
    0.95
    G
    0.93
     pre
    0.91
    Pre
    0.86
    kommer
    0.82
    rive
    0.81
    ish
    0.80
     प्री
    0.79
    ي
    0.79
     و
    0.78
    Act Density 0.018%

    No Known Activations