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

    Neuronpedia

    INDEX
    Explanations

    helpful resources and links

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sources
    0.47
     source
    0.46
    sources
    0.45
    Source
    0.43
     SOURCE
    0.42
    SOURCE
    0.40
    urgent
    0.39
     unsettled
    0.39
    Sources
    0.38
    crisis
    0.38
    POSITIVE LOGITS
     Helpful
    0.54
     hilfreich
    0.53
     Recomend
    0.51
     Links
    0.50
     links
    0.49
     추천
    0.48
     பக்கம்
    0.47
     helpful
    0.46
    links
    0.46
    पूर्ण
    0.46
    Act Density 0.012%

    No Known Activations