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

    Neuronpedia

    INDEX
    Explanations

    fixed point

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     كيف
    -0.09
     illegal
    -0.08
     биз
    -0.08
     هل
    -0.08
     nama
    -0.08
     scary
    -0.08
     strlen
    -0.07
     pilih
    -0.07
     الف
    -0.07
     vall
    -0.07
    POSITIVE LOGITS
     invari
    0.10
     consistently
    0.09
     सार्व
    0.09
    固定
    0.09
     Coordinates
    0.09
     coordinates
    0.08
     puntos
    0.08
     Universal
    0.08
     coordonnées
    0.08
     universal
    0.08
    Act Density 0.019%

    No Known Activations