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

    Neuronpedia

    INDEX
    Explanations

    determine describe

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     crisis
    -0.07
    總統
    -0.07
    纳税人
    -0.07
    菰
    -0.07
    (dest
    -0.07
    顯示
    -0.07
    🍙
    -0.07
    桌上
    -0.07
    	case
    -0.06
     mesmo
    -0.06
    POSITIVE LOGITS
    큘
    0.08
     lugares
    0.08
    坎
    0.08
    Friday
    0.07
    (click
    0.07
     AFF
    0.07
    .SC
    0.07
    /devices
    0.07
    建华
    0.07
    .AddTransient
    0.07
    Act Density 0.065%

    No Known Activations