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

    Neuronpedia

    INDEX
    Explanations

    history and military

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ﺻ
    0.48
     kahi
    0.46
     styl
    0.44
     corticosteroids
    0.44
     zonder
    0.41
     скачать
    0.40
     psychotherapy
    0.39
    lerimiz
    0.39
     soothing
    0.39
     kilos
    0.39
    POSITIVE LOGITS
    Cards
    0.45
    AI
    0.45
    战争
    0.44
    Employment
    0.44
    后
    0.43
    ON
    0.43
    According
    0.43
    Multimedia
    0.42
    Pherson
    0.41
    Ad
    0.41
    Act Density 0.001%

    No Known Activations