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

    Neuronpedia

    INDEX
    Explanations

    guiding plans for

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     inescap
    0.55
     maintenant
    0.55
     ਹੈ
    0.53
     teraz
    0.50
     actuel
    0.49
    ഞ
    0.48
     cunning
    0.48
     utter
    0.47
    figur
    0.47
     आहे
    0.46
    POSITIVE LOGITS
     তাদের
    0.59
    তাদের
    0.56
     purchasers
    0.52
     portfolios
    0.51
    個別
    0.51
     households
    0.51
     raffle
    0.50
    उनके
    0.49
     Certificates
    0.49
     Brokers
    0.48
    Act Density 0.079%

    No Known Activations