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

    Neuronpedia

    INDEX
    Explanations

    chorus marker

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     monasteries
    0.50
     อา
    0.49
    Fa
    0.47
    Ak
    0.46
     manufacturers
    0.45
     tenders
    0.45
     beggars
    0.45
     eyebrows
    0.45
     seasons
    0.45
     faculties
    0.44
    POSITIVE LOGITS
    德国
    0.54
    因而
    0.52
    德國
    0.48
    重要的
    0.46
    民主
    0.46
    腥
    0.46
    痪
    0.44
    纸
    0.43
    诙
    0.43
     проек
    0.42
    Act Density 0.001%

    No Known Activations