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

    Neuronpedia

    INDEX
    Explanations

    chemical composition

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    权力
    0.93
    拒绝
    0.88
    联盟
    0.87
    运营
    0.86
    军队
    0.86
    财政
    0.84
    趔
    0.84
    场景
    0.83
    绩效
    0.83
    监狱
    0.83
    POSITIVE LOGITS
     chemical
    1.47
     chemically
    1.35
     mineral
    1.27
     chemicals
    1.27
     minerals
    1.20
    chemical
    1.18
     impurities
    1.18
     chloride
    1.16
     salts
    1.16
     lignin
    1.15
    Act Density 0.290%

    No Known Activations