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

    Neuronpedia

    INDEX
    Explanations

    next and future references

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     추가
    0.47
     zusätzlichen
    0.47
     additional
    0.45
     thêm
    0.41
     сейчас
    0.41
     tillegg
    0.40
     Additional
    0.40
     dále
    0.40
     още
    0.40
     Ongoing
    0.40
    POSITIVE LOGITS
    Somewhere
    0.40
     कधी
    0.39
    什么时候
    0.38
    З
    0.38
     someday
    0.37
    циа
    0.37
     다음에
    0.36
    Qu
    0.36
     brighter
    0.36
     algum
    0.36
    Act Density 0.026%

    No Known Activations