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

    Neuronpedia

    INDEX
    Explanations

    author

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     flea
    -0.07
     negligible
    -0.07
     College
    -0.07
    ccione
    -0.07
    ��
    -0.07
     hometown
    -0.06
    江苏省
    -0.06
    最合适
    -0.06
     separately
    -0.06
     relie
    -0.06
    POSITIVE LOGITS
    (segment
    0.07
    DA
    0.07
     enfrent
    0.07
    вор
    0.07
    �
    0.06
    멱
    0.06
    品牌形象
    0.06
    ตาร
    0.06
     cod
    0.06
    是怎么
    0.06
    Act Density 0.001%

    No Known Activations