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

    Neuronpedia

    INDEX
    Explanations

    Regions and countries

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	tp
    -0.07
     towers
    -0.07
    .Buffer
    -0.07
    Point
    -0.07
     wolf
    -0.07
     cake
    -0.07
    point
    -0.06
    ature
    -0.06
    \Bridge
    -0.06
    _Double
    -0.06
    POSITIVE LOGITS
     نیست
    0.07
    issent
    0.07
     здійсню
    0.07
    ží
    0.06
    /
↵
↵
    0.06
     про
    0.06
    カテゴリ
    0.06
     braz
    0.06
    加入
    0.06
     simplest
    0.06
    Act Density 0.112%

    No Known Activations