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

    Neuronpedia

    INDEX
    Explanations

    language fragments or word endings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     a
    0.41
     The
    0.39
     only
    0.38
     two
    0.35
     Only
    0.34
     since
    0.33
     four
    0.33
     Two
    0.33
     as
    0.33
     cannot
    0.33
    POSITIVE LOGITS
    انات
    0.37
    签署
    0.35
    ارات
    0.33
     ويكيپيديا
    0.33
    arlı
    0.32
    艳
    0.31
    لمات
    0.31
    عات
    0.31
    uski
    0.30
    cesz
    0.30
    Act Density 0.001%

    No Known Activations