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

    Neuronpedia

    INDEX
    Explanations

    per liter, which is, earthy flavor

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    其实
    1.38
    ))){
    1.38
    ▛
    1.38
    个小时
    1.34
     Deci
    1.27
    炅
    1.27
    讧
    1.27
    เยี่ยม
    1.23
     الصحية
    1.23
    kę
    1.23
    POSITIVE LOGITS
    م
    1.52
    ة
    1.44
    ुअल
    1.38
    ing
    1.37
    х
    1.36
    ాలు
    1.34
    ент
    1.30
    ر
    1.27
    ی
    1.27
    ্ড
    1.26
    Act Density 0.001%

    No Known Activations