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

    Neuronpedia

    INDEX
    Explanations

    types of sections or items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    そして
    0.49
    łach
    0.49
    ै
    0.47
     Wing
    0.47
     Lat
    0.46
     Wines
    0.46
    !
    0.46
     MyHomePage
    0.45
    TypeArguments
    0.45
     nourrir
    0.45
    POSITIVE LOGITS
     করিবে
    0.55
    тный
    0.54
    aop
    0.54
    存于互联网档案馆
    0.53
     innehåller
    0.53
     вариант
    0.53
    сія
    0.53
     સંપૂર્ણ
    0.53
     yksi
    0.53
     centerpiece
    0.52
    Act Density 0.000%

    No Known Activations