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

    Neuronpedia

    INDEX
    Explanations

    composition

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ePub
    -0.07
    Security
    -0.07
     baskı
    -0.07
    Parking
    -0.06
     excursion
    -0.06
     defenses
    -0.06
     goats
    -0.06
    押
    -0.06
    MainActivity
    -0.06
     sẻ
    -0.06
    POSITIVE LOGITS
     фин
    0.06
    .transform
    0.06
     ξ
    0.06
     Haus
    0.06
    ційних
    0.06
     americ
    0.06
     وصلات
    0.06
     empowering
    0.06
    หาร
    0.06
     نسبة
    0.06
    Act Density 0.074%

    No Known Activations