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

    Neuronpedia

    INDEX
    Explanations

    default value or selecting constants

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Becoming
    0.49
     мини
    0.46
    Establishing
    0.44
    кая
    0.43
     contenus
    0.41
     pea
    0.41
    Lifestyle
    0.41
     باستخدام
    0.41
    Becoming
    0.41
     Blogging
    0.41
    POSITIVE LOGITS
    лиш
    0.47
    ഞ്ഞി
    0.47
    INTS
    0.46
     criticised
    0.45
     punches
    0.45
    İL
    0.45
    etzes
    0.45
    ქ
    0.45
    putes
    0.44
     quarrels
    0.43
    Act Density 0.006%

    No Known Activations