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

    Neuronpedia

    INDEX
    Explanations

    water

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     fede
    0.47
     fed
    0.47
    Fed
    0.46
     Fed
    0.43
     फेड
    0.43
     Feder
    0.39
    ᐈ
    0.39
    类型
    0.38
     Types
    0.38
     النوع
    0.38
    POSITIVE LOGITS
    Sources
    0.51
    quellen
    0.46
     sources
    0.46
     Sources
    0.44
    sources
    0.44
     SOURCES
    0.44
    courses
    0.43
    SOURCES
    0.43
    Daily
    0.43
    Courses
    0.42
    Act Density 0.002%

    No Known Activations