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

    Neuronpedia

    INDEX
    Explanations

    professional context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     зміни
    0.48
     ważne
    0.46
    ję
    0.46
     տ
    0.46
     बिल्डिंग
    0.45
     엔
    0.44
     빌
    0.44
     Aktion
    0.44
     밝
    0.44
     incontro
    0.44
    POSITIVE LOGITS
    有一定的
    0.44
    量
    0.44
    ائو
    0.44
    турой
    0.43
    زء
    0.43
    و
    0.43
    يلي
    0.43
    يد
    0.42
     lake
    0.42
     complémentaires
    0.42
    Act Density 0.001%

    No Known Activations