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

    Neuronpedia

    INDEX
    Explanations

    list items and code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    mersive
    0.45
    etica
    0.45
    াভাবিক
    0.43
    linkedExternal
    0.43
    şil
    0.43
    śmy
    0.42
     restrictive
    0.42
    وسي
    0.42
    ซื้อ
    0.42
    ตรง
    0.42
    POSITIVE LOGITS
    ニャ
    0.50
    :
    0.48
     oks
    0.48
     eduk
    0.44
     ytter
    0.44
     analisi
    0.44
     Anu
    0.44
     studie
    0.43
     analiza
    0.43
     지도
    0.42
    Act Density 0.002%

    No Known Activations