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

    Neuronpedia

    INDEX
    Explanations

    member of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sut
    1.09
     leve
    0.97
     ljud
    0.96
     ham
    0.92
    ấu
    0.91
    ors
    0.89
     ملی
    0.88
    スプレイ
    0.87
     सारे
    0.86
     reto
    0.85
    POSITIVE LOGITS
    ați
    1.50
    atical
    1.46
    资格
    1.35
    xico
    1.30
    thom
    1.26
    सभा
    1.22
     iglesia
    1.21
     inférieurs
    1.19
     keluarga
    1.17
     कार्यकारिणी
    1.17
    Act Density 0.070%

    No Known Activations