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

    Neuronpedia

    INDEX
    Explanations

    `=` or `and` operator

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ップ
    0.82
    岖
    0.82
     neigh
    0.81
    ínez
    0.80
     تھا
    0.80
    房价
    0.79
     descuentos
    0.79
     ہیں
    0.78
     تھے
    0.77
     sagittis
    0.77
    POSITIVE LOGITS
    Ду
    0.76
    ام
    0.75
    config
    0.71
    ма
    0.70
    ход
    0.68
    <%
    0.67
    푹
    0.66
    хода
    0.65
    Го
    0.65
    grep
    0.65
    Act Density 0.002%

    No Known Activations