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

    Neuronpedia

    INDEX
    Explanations

    focus on needs or wants

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    MenuActive
    0.46
    允許
    0.46
    !(
    0.45
     ermöglichen
    0.45
     allows
    0.45
    因為
    0.45
     eventuali
    0.45
     allowing
    0.44
    !",
    0.44
    brewer
    0.44
    POSITIVE LOGITS
     solely
    0.48
    議員
    0.45
     संग्रहालय
    0.41
     thuyết
    0.40
     ультра
    0.39
    sole
    0.39
     অতিথি
    0.39
     hapless
    0.39
    ாம்
    0.38
     आमदार
    0.38
    Act Density 0.024%

    No Known Activations