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

    Neuronpedia

    INDEX
    Explanations

    foreign language characters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Cathedral
    0.46
     partake
    0.44
     Chac
    0.44
    सभी
    0.43
     boyhood
    0.43
     كل
    0.43
     siete
    0.43
     Sharm
    0.43
    эри
    0.43
     yell
    0.43
    POSITIVE LOGITS
    อล
    0.47
    的
    0.46
    г
    0.46
    o
    0.44
    v
    0.44
    olition
    0.43
    дра
    0.43
    ิลป
    0.42
    ž
    0.42
    ні
    0.41
    Act Density 0.002%

    No Known Activations