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

    Neuronpedia

    INDEX
    Explanations

    opinions and advice

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cry
    -0.07
     slides
    -0.07
    	parent
    -0.07
     convent
    -0.06
    běhu
    -0.06
     scaled
    -0.06
    -stage
    -0.06
    chein
    -0.06
     쉽
    -0.06
    bundles
    -0.06
    POSITIVE LOGITS
     should
    0.07
     Defence
    0.07
    ?",
    0.06
    .t
    0.06
     ForCanBeConvertedToForeach
    0.06
     Digit
    0.06
    water
    0.06
     Αυ
    0.06
     '">'
    0.06
     Sar
    0.06
    Act Density 0.090%

    No Known Activations