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

    Neuronpedia

    INDEX
    Explanations

    chemical components

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    惩
    0.73
    运营
    0.68
    节奏
    0.67
    权力
    0.66
    体验
    0.63
    统计
    0.63
    风格
    0.63
    盘
    0.62
    场景
    0.60
    选举
    0.59
    POSITIVE LOGITS
     chemically
    1.51
     chemical
    1.35
     lignin
    1.34
     hydrolysis
    1.28
     chemist
    1.27
     hydroly
    1.27
     solubility
    1.26
     sodium
    1.25
     calcium
    1.23
     chloride
    1.23
    Act Density 0.040%

    No Known Activations