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

    Neuronpedia

    INDEX
    Explanations

    debt to income ratio

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     위해
    0.41
     कराया
    0.38
     الفر
    0.38
     صل
    0.38
     Taş
    0.38
     medida
    0.37
    ომ
    0.37
     ทีม
    0.37
     داد
    0.35
    istance
    0.35
    POSITIVE LOGITS
    alth
    0.43
     jpg
    0.42
     высокая
    0.42
     spend
    0.41
     Iceland
    0.41
     Upper
    0.41
    fraction
    0.40
    Iceland
    0.40
    idegg
    0.40
    ็ว
    0.39
    Act Density 0.000%

    No Known Activations