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

    Neuronpedia

    INDEX
    Explanations

    legal documents

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    工业
    -0.09
    idle
    -0.08
     ад
    -0.07
    ῷ
    -0.07
     warehouse
    -0.07
    不到位
    -0.07
     spur
    -0.07
    率达到
    -0.07
     cười
    -0.07
    barcode
    -0.07
    POSITIVE LOGITS
    	version
    0.07
    requent
    0.07
     UK
    0.06
     tempered
    0.06
     mk
    0.06
     girlfriends
    0.06
    �
    0.06
    阶
    0.06
    unciation
    0.06
     spanning
    0.06
    Act Density 0.000%

    No Known Activations