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

    Neuronpedia

    INDEX
    Explanations

    clear your head private

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <unused1903>
    1.09
    𝙡
    1.07
     rudder
    1.04
     luni
    1.04
     estud
    1.00
    LastError
    1.00
    <unused1874>
    1.00
    SystemCall
    0.99
    फाइनल
    0.98
    TimeControl
    0.98
    POSITIVE LOGITS
    ل
    1.03
    it
    0.94
    ेंद्र
    0.94
    cerr
    0.91
    vih
    0.81
    エ
    0.81
     personalize
    0.80
     pamoja
    0.78
    전
    0.78
    girl
    0.78
    Act Density 0.001%

    No Known Activations