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

    Neuronpedia

    INDEX
    Explanations

    geopolitical conflict and strategy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     (
    1.34
    /
    1.04
    (
    1.03
    においても
    0.90
     HIPAA
    0.87
    においては
    0.86
     /
    0.85
     S
    0.82
     annum
    0.82
     B
    0.80
    POSITIVE LOGITS
     تريد
    1.04
     lawmaker
    0.95
    <unused723>
    0.95
     मंजूरी
    0.95
     щоб
    0.94
     لكن
    0.93
    <unused2138>
    0.93
     нужны
    0.92
    向け
    0.91
     помогут
    0.90
    Act Density 0.002%

    No Known Activations