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

    Neuronpedia

    INDEX
    Explanations

    function definition

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     A
    0.79
     including
    0.69
     "
    0.67
    ung
    0.65
     An
    0.61
    ra
    0.61
     ro
    0.61
    시스템
    0.61
     Strukturen
    0.60
     The
    0.60
    POSITIVE LOGITS
    ның
    0.79
    мір
    0.78
     irá
    0.76
    торая
    0.75
    ству
    0.74
     kubwa
    0.73
    ডাক্ট
    0.72
    SOLE
    0.72
     بوتل
    0.71
    txtbtn
    0.71
    Act Density 0.608%

    No Known Activations