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

    Neuronpedia

    INDEX
    Explanations

    advertising and ads

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Decomposition
    0.49
     priest
    0.44
     python
    0.43
     cysteine
    0.42
     gradioApp
    0.41
     discord
    0.41
     PYTHON
    0.40
     ব্যায়াম
    0.40
     жидкости
    0.40
     Embry
    0.39
    POSITIVE LOGITS
     advertising
    1.88
     advertisers
    1.87
     광고
    1.81
    广告
    1.80
     ads
    1.77
     advertiser
    1.76
     Advertising
    1.72
    広告
    1.71
     Ads
    1.70
    廣告
    1.69
    Act Density 0.055%

    No Known Activations