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

    Neuronpedia

    INDEX
    Explanations

    health concerns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    م
    1.14
    ጀት
    0.89
    手的
    0.88
     ولكن
    0.87
    了他
    0.86
    I
    0.84
     αλλά
    0.83
    that
    0.79
     törté
    0.77
    この
    0.76
    POSITIVE LOGITS
     health
    1.54
    <0x80>
    1.44
    र
    1.37
    ;
    1.30
    го
    1.27
    health
    1.16
    د
    1.13
    р
    1.13
    ע
    1.12
     HEALTH
    1.10
    Act Density 0.112%

    No Known Activations