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

    Neuronpedia

    INDEX
    Explanations

    prior toorwhich was

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     آهي
    0.45
     Currently
    0.45
    Tomorrow
    0.45
     obecnie
    0.44
     Tomorrow
    0.44
     huidige
    0.44
     오늘은
    0.43
    今日も
    0.42
     একবার
    0.42
     உள்ளது
    0.42
    POSITIVE LOGITS
     habían
    1.68
     hadn
    1.59
     había
    1.45
     habíamos
    1.43
     havia
    1.37
     had
    1.24
    had
    1.21
     zuvor
    1.20
     prior
    1.18
    之前
    1.13
    Act Density 0.025%

    No Known Activations