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

    Neuronpedia

    INDEX
    Explanations

    depression and mental health conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    un
    1.03
    as
    1.02
    ır
    0.97
    т
    0.93
    {
    0.89
    '
    0.87
     उच्चतम
    0.87
    ي
    0.84
    ុល
    0.84
    د
    0.84
    POSITIVE LOGITS
    ти
    0.83
    chen
    0.74
     depression
    0.70
    ה
    0.70
    ci
    0.68
    siniz
    0.68
     Depression
    0.68
    ⁵
    0.67
    🍱
    0.67
    ות
    0.66
    Act Density 0.008%

    No Known Activations