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

    Neuronpedia

    INDEX
    Explanations

    advertisements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    regulating
    0.46
    reg
    0.46
    regs
    0.45
    regulatory
    0.42
    pul
    0.40
    ario
    0.40
    ereg
    0.39
    tis
    0.38
    uttore
    0.38
    ACCESS
    0.38
    POSITIVE LOGITS
     advertisements
    0.68
     advertisement
    0.65
     ads
    0.62
     adverts
    0.59
     advertis
    0.58
     Ads
    0.57
     Advertisement
    0.56
    广告
    0.55
     Advert
    0.53
     advertise
    0.53
    Act Density 0.000%

    No Known Activations