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

    Neuronpedia

    INDEX
    Explanations

    qualified healthcare

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    James
    0.42
     jean
    0.42
     James
    0.41
     Jean
    0.41
     जे
    0.41
     Jake
    0.40
     Jackpot
    0.40
    Jean
    0.39
     jPanel
    0.38
     Jacques
    0.38
    POSITIVE LOGITS
    healthcare
    0.43
    Healthcare
    0.42
    Sew
    0.39
    Yun
    0.38
    ⟧
    0.38
    Y
    0.38
     السعودي
    0.38
    ilä
    0.38
     sip
    0.37
     Yun
    0.37
    Act Density 0.013%

    No Known Activations