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

    Neuronpedia

    INDEX
    Explanations

    limited offers and urgency

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     formalism
    0.63
     nihil
    0.63
     antagonistic
    0.61
     subordination
    0.61
     subjectivity
    0.60
     asymptotic
    0.59
     manipulating
    0.58
     postulated
    0.58
     doctrina
    0.57
     pseudos
    0.57
    POSITIVE LOGITS
    優惠
    1.14
    优惠
    0.98
     할인
    0.89
     FREE
    0.89
     Premium
    0.86
     Discount
    0.86
     Promo
    0.86
     oferta
    0.84
     offer
    0.84
     Offer
    0.83
    Act Density 0.085%

    No Known Activations