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

    Neuronpedia

    INDEX
    Explanations

    exclamations or surprise

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     because
    0.68
     Porque
    0.66
     Horticultural
    0.64
     Because
    0.64
     converts
    0.64
     Inspire
    0.63
     فقط
    0.62
     প্রয়
    0.62
     perchè
    0.62
     因為
    0.62
    POSITIVE LOGITS
    !
    1.27
    ！
    1.15
    !।
    1.13
    !,
    1.09
    !);
    1.06
    !;
    1.03
    !).
    1.00
    !.
    0.99
    !’
    0.96
    !),
    0.94
    Act Density 0.123%

    No Known Activations