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

    Neuronpedia

    INDEX
    Explanations

    prefix + suffix word formation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    0.39
     (
    0.33
     <
    0.30
     Python
    0.28
     நீங்கள்
    0.27
     Table
    0.27
     {
    0.27
     Tabelle
    0.26
     Gaussian
    0.25
    \
    0.25
    POSITIVE LOGITS
    혔
    0.29
    л
    0.29
    ترین
    0.27
    лиги
    0.26
     carinatis
    0.26
    си
    0.25
    щает
    0.25
    ु
    0.25
    गेटिव
    0.25
    한다
    0.24
    Act Density 0.789%

    No Known Activations