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

    Neuronpedia

    INDEX
    Explanations

    statistical results

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Kann
    -0.07
    CKET
    -0.07
     İz
    -0.06
     Rotterdam
    -0.06
     Něm
    -0.06
    concat
    -0.06
    Narrated
    -0.05
    Im
    -0.05
     bạc
    -0.05
    663
    -0.05
    POSITIVE LOGITS
    ysi
    0.10
    utable
    0.08
    ağın
    0.07
    均
    0.07
     광고
    0.07
     입니다
    0.07
     υπηρε
    0.07
     문의
    0.07
    하면서
    0.07
    _Date
    0.07
    Act Density 0.002%

    No Known Activations