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

    Neuronpedia

    INDEX
    Explanations

    closing braces and semicolons

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    …
    0.40
    ”
    0.38
    }
    0.38
    waitKey
    0.36
    ဆောင်
    0.36
    ющегося
    0.35
    )
    0.35
     similares
    0.35
     Kev
    0.35
    كس
    0.34
    POSITIVE LOGITS
    稅
    0.43
    Ῥ
    0.42
     চীৎকার
    0.40
     아멘
    0.40
     ज्यात
    0.40
    athi
    0.39
    rı
    0.39
    ਡੀ
    0.39
    ndal
    0.38
    ラベル
    0.38
    Act Density 0.021%

    No Known Activations