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

    Neuronpedia

    INDEX
    Explanations

    explanations or why

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ಅವು
    0.42
     apresenta
    0.40
    ):
    0.40
    ਰੇ
    0.40
    )：
    0.40
    ປະກອບ
    0.40
     Kennt
    0.39
    各
    0.39
     ordine
    0.38
     njima
    0.38
    POSITIVE LOGITS
     TikTok
    0.66
     podcast
    0.64
     Podcast
    0.63
     podcasts
    0.63
    iktok
    0.61
    为什么
    0.60
     Instagram
    0.59
     Patreon
    0.57
     why
    0.56
     Millennials
    0.54
    Act Density 0.059%

    No Known Activations