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

    Neuronpedia

    INDEX
    Explanations

    update or edit

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     каждого
    0.55
     chaque
    0.48
     jeweiligen
    0.47
     vrije
    0.47
    それぞれ
    0.45
     każdego
    0.45
     каждой
    0.45
     każde
    0.44
     каждому
    0.44
     Каждый
    0.43
    POSITIVE LOGITS
     updated
    1.31
    Updated
    1.23
     Updated
    1.23
    updated
    1.20
     update
    1.08
    更新
    1.07
    update
    1.03
     aggior
    1.02
    Update
    1.02
     Update
    1.00
    Act Density 0.001%

    No Known Activations