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

    Neuronpedia

    INDEX
    Explanations

    HDCP understanding

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    加载
    0.48
     loaded
    0.47
     ел
    0.45
     Taj
    0.43
     Aeron
    0.43
    个
    0.42
    屏幕
    0.41
     загру
    0.41
    窗口
    0.41
     публи
    0.40
    POSITIVE LOGITS
    implantation
    0.44
    ud
    0.39
     hills
    0.39
    ogas
    0.39
    ydia
    0.39
     stalwart
    0.38
    hect
    0.38
     commences
    0.38
    ent
    0.38
     rebels
    0.38
    Act Density 0.000%

    No Known Activations