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

    Neuronpedia

    INDEX
    Explanations

    focused on or help you

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     o
    0.54
    ,
    0.48
     mol
    0.48
     str
    0.45
     w
    0.44
     das
    0.44
     s
    0.44
     gr
    0.44
     ak
    0.43
     -,
    0.43
    POSITIVE LOGITS
    馇
    0.48
    鲔
    0.46
    সিডেন্ট
    0.45
     осозна
    0.45
     Folklore
    0.44
    unternehmen
    0.44
     народов
    0.44
    Ყ
    0.43
     невероят
    0.43
    வருக்கு
    0.42
    Act Density 0.002%

    No Known Activations