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

    Neuronpedia

    INDEX
    Explanations

    psychiatric conditions and professionals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ية
    2.73
    í
    2.33
    ist
    2.08
    ৪
    2.00
    é
    1.99
    ğin
    1.97
    ás
    1.93
    اد
    1.91
    ăț
    1.91
    м
    1.91
    POSITIVE LOGITS
    corsi
    1.92
    क्षित
    1.88
     وعلى
    1.77
     なっ
    1.75
    ra
    1.69
    taste
    1.62
    ्यूब
    1.59
    ]^{+}$
    1.58
    ként
    1.54
    StringSet
    1.53
    Act Density 0.015%

    No Known Activations