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

    Neuronpedia

    INDEX
    Explanations

    technical documents

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    anson
    -0.08
    呗
    -0.08
     PDF
    -0.07
    인지
    -0.07
    栈
    -0.07
     obvious
    -0.07
    쏨
    -0.07
     thicker
    -0.07
    没事
    -0.07
     Nicholas
    -0.07
    POSITIVE LOGITS
     plan
    0.07
     demolition
    0.07
    ław
    0.07
    plan
    0.07
    底盘
    0.06
    	W
    0.06
     DESIGN
    0.06
    /gtest
    0.06
    ⁅
    0.06
    技法
    0.06
    Act Density 0.297%

    No Known Activations