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

    Neuronpedia

    INDEX
    Explanations

    being there, chatbots, relationships

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Harvesting
    0.51
     Absorption
    0.49
     خی
    0.48
    ۔
    0.48
     Abia
    0.47
    generational
    0.45
     البط
    0.44
    收获
    0.44
    ویت
    0.44
     خیر
    0.44
    POSITIVE LOGITS
    ements
    0.51
     concernant
    0.48
     logiciels
    0.46
     produits
    0.46
     répondre
    0.46
     manifi
    0.45
     digitale
    0.45
     seco
    0.45
    erade
    0.45
    來自
    0.45
    Act Density 0.001%

    No Known Activations