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

    Neuronpedia

    INDEX
    Explanations

    App bar and ui elements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ang
    0.46
    aw
    0.44
     veril
    0.40
    ng
    0.40
     plat
    0.40
    ct
    0.40
    c
    0.40
    igh
    0.39
    nd
    0.39
    有效
    0.39
    POSITIVE LOGITS
    DrawerToggle
    0.46
     hại
    0.44
     Бекер
    0.40
    寞
    0.39
     melibatkan
    0.38
     ಭ
    0.38
     പരി
    0.38
     параметров
    0.37
     apoyo
    0.37
    缦
    0.37
    Act Density 0.001%

    No Known Activations