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

    Neuronpedia

    INDEX
    Explanations

    evidence to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    เพื่อให้
    0.53
     upang
    0.46
    ให้
    0.44
    Чтобы
    0.44
     भी
    0.43
     tạo
    0.43
     ώστε
    0.43
    创建一个
    0.43
     ताकि
    0.42
     aby
    0.42
    POSITIVE LOGITS
     effect
    0.50
     effet
    0.47
     regarding
    0.46
    効果
    0.46
     indicate
    0.45
     効果
    0.44
     Effect
    0.44
     عارفين
    0.43
     тему
    0.42
    效应
    0.42
    Act Density 0.020%

    No Known Activations