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

    Neuronpedia

    INDEX
    Explanations

    decorators and class decorators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    擰
    0.57
    CHEMY
    0.54
    䟧
    0.54
    味噌
    0.53
    𒅁
    0.53
    پيديا
    0.52
     โอ้
    0.52
     পোকামাকড়
    0.51
     مکتی
    0.51
     Règlement
    0.51
    POSITIVE LOGITS
    void
    0.69
     void
    0.62
     null
    0.59
    op
    0.59
     new
    0.58
     "
    0.57
    Object
    0.57
    it
    0.54
     Object
    0.54
    s
    0.54
    Act Density 0.001%

    No Known Activations