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

    Neuronpedia

    INDEX
    Explanations

    sentence terminators or Chinese punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    と思いますが
    0.50
     ecosystems
    0.47
     s
    0.47
     These
    0.47
     (
    0.46
     groups
    0.46
     system
    0.46
     group
    0.46
     这些
    0.46
     and
    0.46
    POSITIVE LOGITS
    ܀
    0.62
    .}$
    0.58
    ។
    0.54
    ል።
    0.54
    。
    0.54
    }$.
    0.50
     ہے۔
    0.49
    です
    0.49
    》。
    0.47
    })$.
    0.47
    Act Density 0.218%

    No Known Activations