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

    Neuronpedia

    INDEX
    Explanations

    space out

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     lingkaran
    0.47
    美好
    0.45
     tentativa
    0.45
    хих
    0.45
    ждением
    0.44
     Runde
    0.43
     erlaubt
    0.42
     meiosis
    0.42
     migliori
    0.41
     deseos
    0.41
    POSITIVE LOGITS
    ,'
    0.53
    '
    0.52
    '।
    0.50
    ত্ব
    0.47
     économ
    0.47
    '،
    0.47
    ’
    0.46
    isse
    0.46
    ,’
    0.46
    branded
    0.46
    Act Density 0.003%

    No Known Activations