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

    Neuronpedia

    INDEX
    Explanations

    call or text

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     اکثر
    0.36
     લગભગ
    0.36
     કેટલાક
    0.36
     대부분
    0.35
    聝
    0.35
     लगभग
    0.35
     ഓരോ
    0.35
     অধিকাংশ
    0.34
    अधिकांश
    0.34
    adə
    0.33
    POSITIVE LOGITS
     Yourself
    0.64
     yourself
    0.60
     Your
    0.58
     your
    0.57
    Your
    0.56
     yourselves
    0.54
    your
    0.49
    yourself
    0.47
    Get
    0.47
     Get
    0.45
    Act Density 0.057%

    No Known Activations