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

    Neuronpedia

    INDEX
    Explanations

    Informational/Expository texts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    รายละเอียด
    -0.09
    ��
    -0.09
    夜夜
    -0.08
     Details
    -0.08
    atter
    -0.08
    详情
    -0.08
    uern
    -0.08
     kën
    -0.08
    iñ
    -0.08
     coucher
    -0.08
    POSITIVE LOGITS
    仍
    0.10
     continuing
    0.10
     hala
    0.10
     fortfarande
    0.10
     сих
    0.10
    	continue
    0.09
     এখনও
    0.09
     Today
    0.09
     edelleen
    0.09
     continuam
    0.09
    Act Density 0.066%

    No Known Activations