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

    Neuronpedia

    INDEX
    Explanations

    door

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    矿山
    -0.07
    西
    -0.07
    (net
    -0.07
    青
    -0.07
    -upper
    -0.07
     Net
    -0.07
    Asian
    -0.07
    .Virtual
    -0.07
    _fence
    -0.06
    Sum
    -0.06
    POSITIVE LOGITS
     door
    0.09
    倒霉
    0.08
    门
    0.07
     Door
    0.07
    ethod
    0.07
    越来越好
    0.07
    ılı
    0.07
    时髦
    0.07
     opportunity
    0.07
    好奇
    0.07
    Act Density 0.014%

    No Known Activations