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

    Neuronpedia

    INDEX
    Explanations

    legal parties

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    وضع
    0.75
     Collaborate
    0.74
    で
    0.72
     determining
    0.72
    علام
    0.71
     রাখতে
    0.70
    到来
    0.70
    ಯೇ
    0.70
    보
    0.68
    要
    0.66
    POSITIVE LOGITS
     wú
    0.80
     pharmacies
    0.80
     hereof
    0.73
    ಂಡ
    0.71
     ቲ
    0.70
     villes
    0.69
     sociétés
    0.68
    들의
    0.66
    argeon
    0.66
     krank
    0.64
    Act Density 0.005%

    No Known Activations