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

    Neuronpedia

    INDEX
    Explanations

    picture or but

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     เพราะ
    0.43
     признаки
    0.43
     नाही
    0.42
     пам
    0.42
     сухо
    0.41
    0
    0.41
     את
    0.41
    ',\
    0.41
    ếc
    0.40
     вашу
    0.40
    POSITIVE LOGITS
    税务
    0.44
     relatório
    0.43
     દરમ
    0.43
     süre
    0.41
     continuo
    0.41
     رکھا
    0.41
    ຕ່
    0.41
     clarity
    0.40
     Chaos
    0.40
     بنگالی
    0.40
    Act Density 0.006%

    No Known Activations