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

    Neuronpedia

    INDEX
    Explanations

    at

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    @param
    -0.07
    电站
    -0.07
    ?family
    -0.07
     testName
    -0.07
    再也没有
    -0.06
     Tribe
    -0.06
    .addListener
    -0.06
    Answers
    -0.06
    (mesh
    -0.06
    -0.06
    POSITIVE LOGITS
    阏
    0.08
    获利
    0.07
    scaling
    0.07
     crunchy
    0.07
    随时
    0.07
     disrupting
    0.07
    💬
    0.06
    一颗
    0.06
    	Run
    0.06
    Persist
    0.06
    Act Density 0.004%

    No Known Activations