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

    Neuronpedia

    INDEX
    Explanations

    academic, student, or researcher discounts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     interpolation
    0.44
     turf
    0.44
    表情
    0.43
     cropping
    0.42
     stable
    0.40
     smoothed
    0.40
     interplay
    0.39
     modulate
    0.39
     ব্যাটিং
    0.39
     crowds
    0.39
    POSITIVE LOGITS
     Discount
    0.96
     discount
    0.91
    Discount
    0.90
     discounts
    0.89
     discounted
    0.85
    discount
    0.85
     할인
    0.84
     descuento
    0.84
     DISCOUNT
    0.80
     Discounts
    0.79
    Act Density 0.051%

    No Known Activations