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

    Neuronpedia

    INDEX
    Explanations

    right-click context menus

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    дем
    0.83
     workmen
    0.76
     SIAM
    0.74
     ಅವ
    0.74
    ROM
    0.73
    ١
    0.72
    畛
    0.72
     Bikes
    0.70
    филлер
    0.70
    DEFGHI
    0.69
    POSITIVE LOGITS
     directly
    0.78
    ister
    0.64
     directement
    0.63
     mus
    0.60
     located
    0.60
     group
    0.60
    的方式
    0.59
     usually
    0.59
     direct
    0.59
     normally
    0.59
    Act Density 0.038%

    No Known Activations