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

    Neuronpedia

    INDEX
    Explanations

    rel

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .appendTo
    -0.07
    .df
    -0.07
     policemen
    -0.07
    واج
    -0.06
    }:{
    -0.06
     SUN
    -0.06
    „P
    -0.06
    менно
    -0.06
    	include
    -0.06
    MEA
    -0.06
    POSITIVE LOGITS
    levelname
    0.06
    OI
    0.06
    ?>↵
    0.06
    (dl
    0.06
    Sci
    0.06
     Emil
    0.06
     Except
    0.06
    %;
    0.06
    구글상위
    0.06
    冰
    0.06
    Act Density 0.002%

    No Known Activations