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

    Neuronpedia

    INDEX
    Explanations

    ads

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Nun
    -0.07
    आई
    -0.07
    運動
    -0.07
    .score
    -0.06
     ensued
    -0.06
    discord
    -0.06
    ，不
    -0.06
     kö
    -0.06
    nist
    -0.06
    ôle
    -0.06
    POSITIVE LOGITS
     ads
    0.18
     Ads
    0.10
     bán
    0.07
    Ads
    0.07
     воздух
    0.07
    209
    0.07
    .expires
    0.07
    론
    0.07
    ẵng
    0.06
    ads
    0.06
    Act Density 0.002%

    No Known Activations