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

    Neuronpedia

    INDEX
    Explanations

    Pr followed by specific nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    inu
    0.46
     або
    0.41
     trans
    0.41
    )&=
    0.40
     declares
    0.39
     ere
    0.38
     או
    0.38
     plotter
    0.38
     dint
    0.38
    াফ
    0.38
    POSITIVE LOGITS
    <unused1007>
    0.44
    Quantidade
    0.42
    粙
    0.42
    ورة
    0.41
    戬
    0.41
    Pr
    0.39
     ගැනීමට
    0.39
    人员
    0.39
     Pronghorn
    0.39
    秣
    0.39
    Act Density 0.018%

    No Known Activations