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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ...]
    -0.07
    ROADCAST
    -0.07
    Warnings
    -0.06
    deadline
    -0.06
    壁
    -0.06
    	controller
    -0.06
    แป
    -0.06
    ipherals
    -0.06
    broker
    -0.06
    меж
    -0.06
    POSITIVE LOGITS
    líč
    0.07
    /gr
    0.07
     stra
    0.07
    غال
    0.06
    トリ
    0.06
    .onNext
    0.06
    人民共和国
    0.06
    DON
    0.06
    写
    0.06
    αρά
    0.06
    Act Density 0.065%

    No Known Activations