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

    Neuronpedia

    INDEX
    Explanations

    wardrobe

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    职务
    -0.07
    分级
    -0.07
    得罪
    -0.07
    .addItem
    -0.07
    ظهر
    -0.07
    输出
    -0.07
    冲
    -0.06
    },
↵
    -0.06
    查看
    -0.06
     ViewState
    -0.06
    POSITIVE LOGITS
     potent
    0.08
    	layer
    0.07
     remembered
    0.07
     mesma
    0.07
    YC
    0.07
    𝙘
    0.06
     zam
    0.06
     actor
    0.06
     себ
    0.06
    _plots
    0.06
    Act Density 0.004%

    No Known Activations