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

    Neuronpedia

    INDEX
    Explanations

    ual

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .calc
    -0.07
    男篮
    -0.07
     Sac
    -0.06
    시험
    -0.06
    asdf
    -0.06
    路
    -0.06
     сек
    -0.06
    峡
    -0.06
    崄
    -0.06
    공
    -0.06
    POSITIVE LOGITS
     masih
    0.07
    datetime
    0.07
     contractual
    0.07
    HorizontalAlignment
    0.07
     także
    0.07
     planta
    0.07
     watermark
    0.07
     trailers
    0.07
     Already
    0.07
     כבר
    0.06
    Act Density 0.003%

    No Known Activations