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

    Neuronpedia

    INDEX
    Explanations

    what the function does

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ಿರ
    0.68
     waving
    0.67
     estuv
    0.64
     saber
    0.64
     আপনার
    0.62
    َ
    0.62
     normalmente
    0.62
    會有
    0.60
     montrent
    0.60
    会有
    0.60
    POSITIVE LOGITS
    وء
    0.64
    Chemical
    0.64
     ગાં
    0.64
     teorema
    0.64
     Environmental
    0.63
     ц
    0.63
     Clair
    0.62
     bessere
    0.61
     Shen
    0.61
     силу
    0.60
    Act Density 0.049%

    No Known Activations