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

    Neuronpedia

    INDEX
    Explanations

    anti- words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ads
    -0.31
    åij¤
    -0.30
    azzo
    -0.26
    åħ¨é¢Ŀ
    -0.25
    Facing
    -0.25
    èµĦæĸĻæĺ¾ç¤º
    -0.25
    æĮĩ导æĦıè§ģ
    -0.24
    ç»ıæŁ¥
    -0.24
     graz
    -0.24
    ADS
    -0.24
    POSITIVE LOGITS
    çħ¨
    0.26
    iphone
    0.25
    -ap
    0.25
    à¸Ĭม
    0.25
     remote
    0.24
    oram
    0.24
     tert
    0.24
    remote
    0.23
    ynet
    0.23
     addAction
    0.23
    Act Density 0.037%

    No Known Activations