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

    Neuronpedia

    INDEX
    Explanations

    API and legal text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    區域
    -0.07
     aVar
    -0.07
    沁
    -0.07
    ناق
    -0.07
    פלא
    -0.07
    -Q
    -0.07
     Xiaomi
    -0.07
    ꒪
    -0.06
    àng
    -0.06
    ugeot
    -0.06
    POSITIVE LOGITS
     finishes
    0.08
     PHI
    0.07
     finishing
    0.07
    机
    0.07
    	
↵
    0.07
    纸
    0.07
    _processor
    0.07
    _gradient
    0.07
    "])↵
    0.07
     결과
    0.07
    Act Density 0.006%

    No Known Activations