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

    Neuronpedia

    INDEX
    Explanations

    initiative aimed at or designed for

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    tahun
    1.09
    з
    1.09
    д
    0.95
    sis
    0.92
    ל
    0.92
    reira
    0.89
     that
    0.88
    л
    0.85
    sin
    0.84
    sen
    0.84
    POSITIVE LOGITS
    ية
    1.23
    는
    1.19
    ő
    1.09
    是
    1.05
    ە
    1.03
    ע
    1.01
    써
    1.00
    ાન
    0.99
    é
    0.99
    生
    0.98
    Act Density 0.002%

    No Known Activations