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

    Neuronpedia

    INDEX
    Explanations

    verified accuracy, funding, languages, claims

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ách
    0.46
     zależ
    0.46
    ithmet
    0.46
     Joz
    0.45
     गुंत
    0.44
    ំប
    0.42
    hoven
    0.42
     segundo
    0.41
    तांत्रिक
    0.41
     शिवाय
    0.41
    POSITIVE LOGITS
    現金
    0.50
    ).
    0.43
    偉
    0.41
     pebble
    0.41
    靑
    0.41
     הא
    0.39
     amts
    0.39
    nullptr
    0.39
    廣
    0.38
     canoe
    0.38
    Act Density 0.004%

    No Known Activations