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

    Neuronpedia

    INDEX
    Explanations

    products

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     花
    -0.07
    ograf
    -0.06
    ูก
    -0.06
     право
    -0.06
     الرئيس
    -0.06
     أفضل
    -0.06
    เช
    -0.06
    Ka
    -0.06
     Coord
    -0.06
     кілька
    -0.06
    POSITIVE LOGITS
     Tween
    0.07
     Homes
    0.07
     Goods
    0.07
     Directive
    0.07
     tôi
    0.06
    Introduction
    0.06
     Going
    0.06
    顶
    0.06
    .enumer
    0.06
     Taş
    0.06
    Act Density 0.028%

    No Known Activations