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

    Neuronpedia

    INDEX
    Explanations

    reputation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ä
    1.09
    än
    0.83
     modellen
    0.80
     It
    0.79
    ain
    0.78
     terug
    0.78
     kiezen
    0.77
     verwend
    0.74
     Protestants
    0.73
     There
    0.72
    POSITIVE LOGITS
     reputation
    1.15
     reputations
    1.13
    리
    0.91
    도
    0.91
    اد
    0.87
     Reputation
    0.87
    에
    0.87
    스
    0.87
    ahari
    0.82
    फोल
    0.79
    Act Density 0.028%

    No Known Activations