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

    Neuronpedia

    INDEX
    Explanations

    makes sense investing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     trick
    0.84
    னமாக
    0.84
    갑
    0.84
     दश
    0.84
    ên
    0.83
     рук
    0.81
     opportunities
    0.81
    潢
    0.81
     Episodes
    0.81
    н
    0.80
    POSITIVE LOGITS
    everything
    1.18
     bolsillo
    1.09
    すべての
    1.09
     totalidad
    1.09
    ের
    1.06
    全ての
    1.04
     credo
    1.03
     वर्षी
    1.01
     প্রেক্ষিতে
    1.01
    eaa
    1.01
    Act Density 0.002%

    No Known Activations