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

    Neuronpedia

    INDEX
    Explanations

    5

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    usk
    -0.07
    xbd
    -0.07
    本报记者
    -0.07
     evaluating
    -0.07
     dhe
    -0.07
    𝙡
    -0.07
     bottoms
    -0.07
    蠢
    -0.06
     oi
    -0.06
     transporting
    -0.06
    POSITIVE LOGITS
     từ
    0.07
     Ведь
    0.07
    entai
    0.07
    rientation
    0.07
    	BYTE
    0.07
     WINDOW
    0.07
     ведь
    0.07
    -Methods
    0.07
    חי
    0.07
    Separator
    0.07
    Act Density 0.002%

    No Known Activations