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

    Neuronpedia

    INDEX
    Explanations

    selecting text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     below
    -0.09
    няя
    -0.07
    .Types
    -0.07
    -described
    -0.07
     아래
    -0.07
    AxisSize
    -0.07
     envision
    -0.07
    ('''
    -0.06
    uppe
    -0.06
    ‽
    -0.06
    POSITIVE LOGITS
    (Game
    0.07
     giorn
    0.07
    	Global
    0.07
    长江
    0.06
    struct
    0.06
     Başkan
    0.06
    ów
    0.06
     Gol
    0.06
    ander
    0.06
     geht
    0.06
    Act Density 0.052%

    No Known Activations