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

    Neuronpedia

    INDEX
    Explanations

    payment terms and agreement clauses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    攻击
    0.63
    现象
    0.58
    皞
    0.58
    个体
    0.57
    图形
    0.57
    大脑
    0.57
    引导
    0.56
    鸣
    0.56
    恐惧
    0.55
    织
    0.55
    POSITIVE LOGITS
     contractual
    1.14
     agreed
    1.06
     payments
    1.00
    payments
    0.88
     contract
    0.87
     clause
    0.86
    contract
    0.84
    payment
    0.84
     payment
    0.80
     clauses
    0.79
    Act Density 0.112%

    No Known Activations