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

    Neuronpedia

    INDEX
    Explanations

    references to press releases and announcements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    press release and announcement

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     le
    -0.25
    ind
    -0.24
     mental
    -0.22
     l
    -0.21
     h
    -0.21
     mata
    -0.20
    Koordinaten
    -0.20
    hasMore
    -0.20
     im
    -0.19
    int
    -0.19
    POSITIVE LOGITS
     announcement
    1.01
     announcements
    0.98
     announcing
    0.97
    MLLoader
    0.95
     Announcement
    0.94
     Announcements
    0.92
    announcement
    0.91
     müſſen
    0.87
    swire
    0.87
    <unused23>
    0.87
    Act Density 0.004%

    No Known Activations