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

    Neuronpedia

    INDEX
    Explanations

    multilingual context

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     누
    0.43
    누
    0.36
    매
    0.35
    基本的
    0.34
     매
    0.34
     disclose
    0.34
     ಸಂಬಂಧ
    0.34
     Sagan
    0.34
    柟
    0.34
    CRIPTOR
    0.33
    POSITIVE LOGITS
    ReaderWriter
    0.39
     Conc
    0.36
    Conc
    0.36
    jes
    0.35
    思う
    0.35
     conc
    0.34
    jonal
    0.34
    Sync
    0.34
    ಧಾನ
    0.33
    }"),
    0.33
    Act Density 0.000%

    No Known Activations