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

    Neuronpedia

    INDEX
    Explanations

    Abbreviations and definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    utiérrez
    0.50
     सेलिब्र
    0.48
     satış
    0.48
    venida
    0.47
     negócios
    0.46
     preços
    0.46
    ورٹی
    0.46
    涝
    0.45
     શુભેચ્છ
    0.45
     yaşanan
    0.45
    POSITIVE LOGITS
     x
    0.61
     l
    0.55
     algebra
    0.54
     C
    0.54
     t
    0.53
    x
    0.53
     d
    0.52
    C
    0.52
    M
    0.51
     D
    0.50
    Act Density 0.002%

    No Known Activations