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

    Neuronpedia

    INDEX
    Explanations

    discount

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Range
    0.43
    Specific
    0.39
    崱
    0.39
    Instruments
    0.36
    循環
    0.36
    པ་
    0.36
     varying
    0.36
    ይን
    0.36
     जहां
    0.35
     দর
    0.35
    POSITIVE LOGITS
     discounting
    0.48
    大丈夫
    0.44
     confrontations
    0.42
     discounts
    0.41
     descuentos
    0.41
     desconto
    0.41
     DISCOUNT
    0.40
     Discounts
    0.40
     ocasi
    0.40
     discount
    0.39
    Act Density 0.000%

    No Known Activations