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

    Neuronpedia

    INDEX
    Explanations

    Foursquare

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     imagination
    -0.07
     бла
    -0.07
    (full
    -0.07
    dition
    -0.07
    問題
    -0.06
    害
    -0.06
    そこ
    -0.06
    (direction
    -0.06
    νι
    -0.06
    ден
    -0.06
    POSITIVE LOGITS
     Yelp
    0.12
     Zuckerberg
    0.06
    ăn
    0.06
    	stat
    0.06
     Tim
    0.06
     Occupy
    0.06
    ुप
    0.06
    XS
    0.06
     roommate
    0.06
    etype
    0.06
    Act Density 0.001%

    No Known Activations