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

    Neuronpedia

    INDEX
    Explanations

    derivative of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     물
    0.46
     École
    0.45
     Cuomo
    0.44
     Lina
    0.43
    ﻝ
    0.43
     जीवन
    0.43
     Él
    0.43
     Ecole
    0.43
     Describes
    0.43
     системой
    0.42
    POSITIVE LOGITS
     podia
    0.42
    ตรง
    0.39
    popup
    0.38
     foy
    0.35
     confidential
    0.35
     cords
    0.35
     stick
    0.35
    षिक
    0.34
    PopupButton
    0.34
    buildings
    0.34
    Act Density 0.001%

    No Known Activations