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

    Neuronpedia

    INDEX
    Explanations

    offensive content requests

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ምንም
    0.50
    efficiency
    0.46
    ジネス
    0.44
    ତ୍
    0.43
    produkte
    0.43
     omnichannel
    0.43
    prosperity
    0.43
    hotels
    0.42
    XR
    0.42
     soluções
    0.42
    POSITIVE LOGITS
     Sometimes
    0.43
     False
    0.43
    经历
    0.43
     jeunes
    0.41
     सत्र
    0.41
     children
    0.41
     Comparisons
    0.41
     Zhou
    0.41
     노래
    0.41
     bagi
    0.41
    Act Density 0.011%

    No Known Activations