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

    Neuronpedia

    INDEX
    Explanations

    3

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    aspberry
    -0.07
     restart
    -0.07
     phó
    -0.07
    (num
    -0.07
    						
↵
    -0.07
     router
    -0.07
     Department
    -0.07
    êu
    -0.07
     ofere
    -0.06
    可愛
    -0.06
    POSITIVE LOGITS
    集体经济
    0.08
    强烈
    0.08
    ymi
    0.07
    平衡
    0.07
    .Space
    0.07
    .poly
    0.07
    疯
    0.07
    电子产品
    0.07
    หม
    0.07
    .cent
    0.07
    Act Density 0.016%

    No Known Activations