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

    Neuronpedia

    INDEX
    Explanations

    main function signature

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     köpek
    0.42
    Genuine
    0.41
     δι
    0.40
     cerim
    0.40
    smöglichkeiten
    0.39
     مل
    0.38
     genuine
    0.38
     hài
    0.38
    的价格
    0.38
     سعر
    0.38
    POSITIVE LOGITS
    bh
    0.41
    (){
    0.40
    image
    0.40
    category
    0.39
    ally
    0.38
    ({
    0.38
    active
    0.38
    furn
    0.38
     batu
    0.38
    tn
    0.38
    Act Density 0.006%

    No Known Activations