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

    Neuronpedia

    INDEX
    Explanations

    . :: *

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ع
    0.57
     u
    0.50
    ensure
    0.49
     у
    0.47
    した
    0.46
     holiness
    0.46
    une
    0.46
     it
    0.45
     sig
    0.45
     departe
    0.45
    POSITIVE LOGITS
    шаем
    0.47
     ಅನುಪಾತ
    0.46
    син
    0.45
    стями
    0.45
     массива
    0.43
     spost
    0.43
     thrott
    0.43
    кала
    0.43
    <0xBB>
    0.42
    ంటున్నారు
    0.42
    Act Density 0.000%

    No Known Activations