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

    Neuronpedia

    INDEX
    Explanations

    asking how you are today

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     unquestion
    0.75
    我相信
    0.72
     बारी
    0.69
     principles
    0.67
    returnValues
    0.66
     distrust
    0.66
     believe
    0.65
     contradictory
    0.64
     credibility
    0.63
     weakens
    0.63
    POSITIVE LOGITS
    Today
    1.39
    今天
    1.38
     today
    1.28
     Today
    1.27
     oggi
    1.27
     сегодня
    1.24
     vandaag
    1.19
     hoje
    1.18
     сьогодні
    1.16
    today
    1.16
    Act Density 0.253%

    No Known Activations