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

    Neuronpedia

    INDEX
    Explanations

    metal accentsworn seatingEarly RequirementsJosh Muzyka

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     distribution
    0.41
     mystery
    0.40
     museum
    0.38
     intense
    0.37
     former
    0.37
     poetic
    0.37
    express
    0.36
    ulnerable
    0.36
     Museum
    0.36
     mental
    0.36
    POSITIVE LOGITS
    👜
    0.45
     ষষ্ঠ
    0.42
     وکړئ
    0.42
    viat
    0.41
     véhicules
    0.41
     inj
    0.40
     ५
    0.40
     cáo
    0.40
     নামে
    0.40
     Шрифт
    0.40
    Act Density 0.001%

    No Known Activations