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

    Neuronpedia

    INDEX
    Explanations

    playful contexts and descriptive qualities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    тел
    0.35
    했고
    0.35
    টিশ
    0.32
    ganggu
    0.32
    ות
    0.31
    сион
    0.31
    unpriv
    0.31
    ут
    0.30
    ensible
    0.30
    టర్‌
    0.30
    POSITIVE LOGITS
     All
    0.30
     Are
    0.30
     Pleasure
    0.30
     !
    0.29
     is
    0.29
     I
    0.29
     Delight
    0.29
     Starring
    0.29
     View
    0.28
    !
    0.28
    Act Density 0.000%

    No Known Activations