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

    Neuronpedia

    INDEX
    Explanations

    aesthetic appeals, value, style

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    耠
    0.71
    崞
    0.63
    皞
    0.62
    攙
    0.62
    瘧
    0.61
    涀
    0.61
    齬
    0.61
    骯
    0.60
    栝
    0.60
    拃
    0.60
    POSITIVE LOGITS
    颜值
    0.89
    性价比
    0.77
    打造
    0.70
     exquisite
    0.69
    这款
    0.69
    精致
    0.68
     exquis
    0.68
    搭配
    0.66
    风格
    0.66
    小
    0.66
    Act Density 0.008%

    No Known Activations