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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Dit
    -0.07
     ####
    -0.06
    िब
    -0.06
    라이
    -0.06
        	↵
    -0.06
    เหล
    -0.06
     attitude
    -0.06
    َت
    -0.06
    みたい
    -0.06
    598
    -0.06
    POSITIVE LOGITS
    监听页面
    0.06
     liable
    0.06
     Göz
    0.06
    cdb
    0.06
     udělat
    0.06
    /pop
    0.06
     cherish
    0.06
    .subplot
    0.06
    ULAR
    0.06
     Госп
    0.06
    Act Density 0.007%

    No Known Activations