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

    Neuronpedia

    INDEX
    Explanations

    end of sentence punctuation followed by pronoun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ↵↵
    0.52
    other
    0.48
    ad
    0.43
    }
    0.43
    ic
    0.42
    ed
    0.41
    res
    0.41
    int
    0.41
    и
    0.38
    class
    0.38
    POSITIVE LOGITS
     Tämä
    0.73
     이건
    0.65
     Acest
    0.65
     이는
    0.60
     Đây
    0.60
     これは
    0.60
     وهذا
    0.59
     Özellikle
    0.59
     Diese
    0.59
     Ensures
    0.58
    Act Density 5.083%

    No Known Activations