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

    Neuronpedia

    INDEX
    Explanations

    discount valuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    铁
    0.59
    辎
    0.54
    协助
    0.54
    面积
    0.54
    ńczy
    0.53
    破坏
    0.52
    忆
    0.52
    吴
    0.52
    机械
    0.51
    ữu
    0.50
    POSITIVE LOGITS
     discounted
    0.95
     discounting
    0.89
     valuation
    0.87
     discount
    0.81
    discount
    0.80
     valuations
    0.77
     DISCOUNT
    0.73
    Discount
    0.72
     financial
    0.69
     finance
    0.69
    Act Density 0.065%

    No Known Activations