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

    Neuronpedia

    INDEX
    Explanations

    original

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     elective
    -0.06
    ieran
    -0.06
     amis
    -0.06
    	k
    -0.06
    عکس
    -0.06
     जय
    -0.06
    RICS
    -0.06
     UCLA
    -0.06
    ////
    -0.06
     apl
    -0.06
    POSITIVE LOGITS
    .getChild
    0.07
     россий
    0.07
     décor
    0.07
     کمتر
    0.07
    Desktop
    0.06
    =$((
    0.06
     cosmetic
    0.06
     виготов
    0.06
     differed
    0.06
    .build
    0.06
    Act Density 0.005%

    No Known Activations