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

    Neuronpedia

    INDEX
    Explanations

    origin of concepts and words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ة
    1.13
    ה
    1.13
    க
    1.11
    न
    1.09
    y
    1.08
    ת
    1.04
    en
    1.03
    tic
    1.03
    tos
    1.03
    ా
    1.01
    POSITIVE LOGITS
     Origins
    1.16
     происхождения
    1.15
     origins
    1.10
     origen
    1.07
     incertid
    1.06
     bekend
    1.05
     origine
    1.05
     origin
    1.04
     dalle
    1.04
     откуда
    1.03
    Act Density 0.019%

    No Known Activations