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

    Neuronpedia

    INDEX
    Explanations

    advertise, advertise, advertised

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     व्
    0.40
     kontra
    0.38
    还
    0.38
    setLookAndFeel
    0.37
     هيبقى
    0.36
    wiek
    0.35
    ᖓ
    0.34
    momentum
    0.34
    गली
    0.34
    ডিও
    0.33
    POSITIVE LOGITS
     advertised
    0.93
     рекла
    0.91
     advertise
    0.88
     advertisement
    0.86
     광고
    0.84
    Advert
    0.82
     advertisements
    0.82
     advert
    0.80
     reklam
    0.80
     Advertisement
    0.79
    Act Density 0.000%

    No Known Activations