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

    Neuronpedia

    INDEX
    Explanations

    whether

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    aint
    -0.26
    åĨĴ
    -0.26
    avors
    -0.25
    stamp
    -0.25
     printing
    -0.24
    ä¸Ĭå®ĺ
    -0.24
    rico
    -0.24
    Printing
    -0.24
    ainting
    -0.24
    rous
    -0.24
    POSITIVE LOGITS
    opensource
    0.27
    çĥŃéŨ
    0.27
    	Copyright
    0.25
    以ä¸ĭæĺ¯
    0.24
     accepted
    0.24
    就被
    0.24
     blown
    0.24
    æĺ¯ä¸įåı¯èĥ½
    0.24
     intelligent
    0.23
     settled
    0.23
    Act Density 0.000%

    No Known Activations