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

    Neuronpedia

    INDEX
    Explanations

    orders, timelines, recipes, mutual, people

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    "});
    1.62
     هنگام
    1.59
     haunts
    1.40
    "}}
    1.38
    ্সি
    1.36
    RouteChange
    1.35
     lymphocytes
    1.34
    ならない
    1.33
     seguros
    1.33
     дети
    1.32
    POSITIVE LOGITS
    ле
    1.67
    in
    1.63
    ков
    1.61
    x
    1.47
    е
    1.46
    ль
    1.45
    ні
    1.41
    не
    1.38
    w
    1.37
    i
    1.34
    Act Density 0.001%

    No Known Activations