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

    Neuronpedia

    INDEX
    Explanations

    stock media and news outlets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Courtesy
    0.68
    Courtesy
    0.65
    Photo
    0.61
     Photo
    0.58
     courtesy
    0.56
     photo
    0.55
    photo
    0.54
     ©
    0.52
    Photos
    0.50
     照片
    0.49
    POSITIVE LOGITS
     EPA
    0.52
    EPA
    0.52
     TikTok
    0.48
     handed
    0.46
     UGC
    0.46
     tiktok
    0.46
     SW
    0.43
     PA
    0.42
     Tiktok
    0.42
     supplied
    0.40
    Act Density 0.001%

    No Known Activations