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

    Neuronpedia

    INDEX
    Explanations

    individual cells

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    批评
    0.76
    新闻
    0.75
    财政
    0.74
     कानून
    0.71
    之时
    0.71
    骗
    0.71
    联邦
    0.70
    职位
    0.70
    经纪
    0.70
    谴
    0.70
    POSITIVE LOGITS
     surface
    0.77
     trapped
    0.75
     geometry
    0.74
     layer
    0.73
     thermal
    0.72
     internal
    0.72
     coating
    0.72
     cavities
    0.72
     convective
    0.72
     thermally
    0.72
    Act Density 0.139%

    No Known Activations