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

    Neuronpedia

    INDEX
    Explanations

    genealogy and genealogical research

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ádza
    1.76
    С
    1.66
    ع
    1.64
     rebuke
    1.58
    iciency
    1.56
    Ե
    1.56
     replay
    1.55
     Amnesty
    1.54
     semiconductor
    1.54
     operable
    1.54
    POSITIVE LOGITS
    о
    2.02
    ಿಂದ
    1.79
    ︎
    1.75
     cwd
    1.70
     svých
    1.69
    𝐦
    1.64
     ViewBag
    1.62
    𝐤
    1.62
    necks
    1.61
    ͑
    1.61
    Act Density 0.001%

    No Known Activations