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

    Neuronpedia

    INDEX
    Explanations

    birth and upbringing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     stockage
    0.40
     leaderboard
    0.40
     দিচ্ছেন
    0.40
     seman
    0.39
     resting
    0.39
     cease
    0.38
     spreads
    0.38
     برقرار
    0.37
    걀
    0.37
     Resting
    0.37
    POSITIVE LOGITS
     upbringing
    1.78
     born
    1.66
    Raised
    1.65
     raised
    1.62
     Raised
    1.62
     grew
    1.61
    raised
    1.52
    Born
    1.48
     Born
    1.46
     geboren
    1.41
    Act Density 0.044%

    No Known Activations