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

    Neuronpedia

    INDEX
    Explanations

    China, banks, lie, charm

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     biztons
    0.47
     airson
    0.44
     fontos
    0.42
     belangrijke
    0.42
     vigt
    0.42
     oficialmente
    0.41
     viktigt
    0.40
     سلسلے
    0.40
    轫
    0.40
    ंसाठी
    0.39
    POSITIVE LOGITS
     ઓળ
    0.47
     άλλα
    0.44
     scorsa
    0.42
    kl
    0.41
     দেখলাম
    0.41
    ۲
    0.40
    代謝
    0.40
     afgelopen
    0.39
    grat
    0.39
    mml
    0.38
    Act Density 0.004%

    No Known Activations