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

    Neuronpedia

    INDEX
    Explanations

    voting

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ounds
    -0.07
    的特点
    -0.07
    อก
    -0.07
    ヮ
    -0.07
    tep
    -0.07
     Hay
    -0.07
    ﭟ
    -0.07
     danmark
    -0.07
    	es
    -0.07
    <Document
    -0.07
    POSITIVE LOGITS
    袜
    0.07
    _visual
    0.07
     osp
    0.07
     uptime
    0.07
     earliest
    0.07
    STIT
    0.06
    odu
    0.06
     ICT
    0.06
     crem
    0.06
     deco
    0.06
    Act Density 0.001%

    No Known Activations