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

    Neuronpedia

    INDEX
    Explanations

    setting states or logic

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     दर्ज
    0.41
     函数
    0.40
     функция
    0.40
    减少
    0.39
     Função
    0.39
    函数
    0.39
     oyn
    0.39
     зад
    0.37
     Функция
    0.37
    攪
    0.37
    POSITIVE LOGITS
    toggle
    0.47
     toggle
    0.43
     Schmitt
    0.43
     Toggle
    0.43
     truths
    0.40
     Collins
    0.39
    Truth
    0.39
     logic
    0.38
     Truth
    0.38
    Masters
    0.38
    Act Density 0.005%

    No Known Activations