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

    Neuronpedia

    INDEX
    Explanations

    espionage and intelligence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    开发者
    0.50
     कार्बो
    0.47
    迁移
    0.47
    벅
    0.46
    㖷
    0.46
    喳
    0.46
     alegria
    0.45
     радо
    0.45
     மகிழ்ச்ச
    0.45
     spaceShip
    0.44
    POSITIVE LOGITS
     espionage
    1.71
     clandestine
    1.58
     covert
    1.41
     spies
    1.34
     clandest
    1.33
     spy
    1.31
     खुफिया
    1.27
     CIA
    1.24
    諜
    1.23
     spying
    1.22
    Act Density 0.081%

    No Known Activations