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

    Neuronpedia

    INDEX
    Explanations

    AI professionals and roles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    梶
    0.42
    主要
    0.42
    ంచ్
    0.41
    由来
    0.40
    所の
    0.38
     vuccati
    0.38
    プローチ
    0.38
    actyl
    0.38
    椒
    0.38
     precedente
    0.37
    POSITIVE LOGITS
     resonate
    0.38
     malattie
    0.38
     permeate
    0.35
     ironically
    0.35
     extrême
    0.35
    大家
    0.34
     மரிய
    0.34
     eerie
    0.34
     merci
    0.34
     permeates
    0.34
    Act Density 0.002%

    No Known Activations