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

    Neuronpedia

    INDEX
    Explanations

    reputation and brand building

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    τρέ
    0.71
    SuppressLint
    0.63
     bialgebra
    0.63
    romino
    0.62
    vart
    0.62
    readlines
    0.62
    搅拌
    0.62
     températures
    0.61
    湍
    0.61
    νει
    0.61
    POSITIVE LOGITS
     reputation
    3.42
     Reputation
    2.93
     reputations
    2.82
     credibility
    2.67
     reput
    2.66
     prestige
    2.13
     prestigio
    1.97
     notoriety
    1.84
     brand
    1.84
     प्रतिष्ठा
    1.83
    Act Density 0.952%

    No Known Activations