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

    Neuronpedia

    INDEX
    Explanations

    company names or item names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ഹ്ലാ
    0.44
     तीस
    0.41
     canoes
    0.41
    ع
    0.41
    餸
    0.40
     wills
    0.40
     passers
    0.40
     เนาะ
    0.40
     airplanes
    0.40
    র্ষি
    0.40
    POSITIVE LOGITS
    *
    0.50
    '
    0.48
    \*
    0.46
    \
    0.43
    ,
    0.43
    ＆
    0.42
     ،
    0.41
    ডিয়া
    0.39
    ide
    0.38
    ственный
    0.38
    Act Density 0.177%

    No Known Activations