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

    Neuronpedia

    INDEX
    Explanations

    information

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Micro
    -0.08
    净土
    -0.07
    Yo
    -0.07
     Doctor
    -0.07
     مرة
    -0.07
    igu
    -0.07
     CURL
    -0.07
    حماس
    -0.07
    琴
    -0.06
    	delete
    -0.06
    POSITIVE LOGITS
     וכמובן
    0.07
    报送
    0.07
     '"+
    0.07
    有害
    0.07
    應用
    0.07
    /setup
    0.06
    )",↵
    0.06
    逮
    0.06
     >",
    0.06
    .Inter
    0.06
    Act Density 0.001%

    No Known Activations