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

    Neuronpedia

    INDEX
    Explanations

    awareness

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     الذي
    0.51
     Stimme
    0.46
    تي
    0.46
    heme
    0.46
    ת
    0.46
     Anakin
    0.45
     طلبه
    0.45
     aprendizaje
    0.45
    الإ
    0.44
     vera
    0.44
    POSITIVE LOGITS
     awareness
    0.99
     aware
    0.88
    awareness
    0.80
     Awareness
    0.79
    Aware
    0.77
     Aware
    0.68
    aware
    0.67
     consciousness
    0.67
    意識
    0.63
    consciousness
    0.61
    Act Density 0.074%

    No Known Activations