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

    Neuronpedia

    INDEX
    Explanations

    difference

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tac
    -0.07
     경기
    -0.06
     lol
    -0.06
    َب
    -0.06
    StackNavigator
    -0.06
     colonial
    -0.06
     Barbar
    -0.06
    踏
    -0.06
    Larry
    -0.06
    conf
    -0.06
    POSITIVE LOGITS
     DAYS
    0.08
     physique
    0.07
     Days
    0.07
    ению
    0.07
     within
    0.07
     window
    0.07
    	delay
    0.07
    ฤด
    0.07
    );}
    0.07
    )}
    0.07
    Act Density 0.015%

    No Known Activations