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

    Neuronpedia

    INDEX
    Explanations

    date and time related calculation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    们
    0.26
    im
    0.25
     Transforming
    0.25
    影响力
    0.24
    O
    0.24
    两
    0.24
    ющими
    0.24
    ‌پ
    0.24
    在
    0.24
     Education
    0.24
    POSITIVE LOGITS
     moet
    0.27
     Februari
    0.27
     posibles
    0.26
     febbraio
    0.25
     kandid
    0.25
    asjonen
    0.25
     berapa
    0.24
    。.
    0.24
     cepat
    0.24
     on
    0.24
    Act Density 0.215%

    No Known Activations