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

    Neuronpedia

    INDEX
    Explanations

    Encoded text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     quanto
    -0.08
    ıklı
    -0.08
     SYS
    -0.07
     quant
    -0.07
     eros
    -0.07
    #[
    -0.07
    uant
    -0.07
    -connect
    -0.06
     genders
    -0.06
     bottleneck
    -0.06
    POSITIVE LOGITS
    的观点
    0.08
     dünyan
    0.07
    .);↵
    0.07
    的背后
    0.07
    建筑业
    0.07
     Jewelry
    0.07
    �
    0.07
    _DEST
    0.07
    /↵↵
    0.06
    getCurrent
    0.06
    Act Density 0.003%

    No Known Activations