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

    Neuronpedia

    INDEX
    Explanations

    highway road numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     exhaustion
    -0.07
    公开招聘
    -0.07
    性疾病
    -0.07
    bersome
    -0.07
    켬
    -0.07
    dest
    -0.07
    /month
    -0.06
    くれ
    -0.06
    很长时间
    -0.06
    十年
    -0.06
    POSITIVE LOGITS
    	doc
    0.08
    (input
    0.07
     GDP
    0.07
     ancestors
    0.07
    好不好
    0.07
    ificial
    0.07
    𝚍
    0.07
    𝐌
    0.07
     кнопк
    0.06
    Instructions
    0.06
    Act Density 0.030%

    No Known Activations