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

    Neuronpedia

    INDEX
    Explanations

    German 'um' prefix

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    س
    1.23
    سون
    1.09
    с
    1.05
    ס
    0.91
     године
    0.83
    ى
    0.83
    后再
    0.80
    يد
    0.78
    ר
    0.78
    ميم
    0.77
    POSITIVE LOGITS
     on
    1.30
    s
    1.11
     and
    1.06
     or
    1.05
    RI
    1.05
    IC
    1.02
    kannya
    1.00
    et
    0.97
     om
    0.97
    त
    0.94
    Act Density 0.001%

    No Known Activations