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

    Neuronpedia

    INDEX
    Explanations

    aware of something

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    الإ
    0.47
    зулта
    0.44
    ிற்கும்
    0.43
    تيجة
    0.40
    تاة
    0.40
    ૧
    0.39
    widetilde
    0.39
    Ми
    0.39
    ٧
    0.39
    Ма
    0.39
    POSITIVE LOGITS
     of
    0.73
     aware
    0.64
    NESS
    0.59
    ness
    0.57
    aware
    0.55
    Aware
    0.55
     Aware
    0.53
     của
    0.51
     awareness
    0.50
     bahwa
    0.50
    Act Density 0.010%

    No Known Activations