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

    Neuronpedia

    INDEX
    Explanations

    opposite of, or contrast

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Woche
    0.42
     can
    0.42
     По
    0.41
     Day
    0.41
    今日も
    0.41
     Crafted
    0.40
     Recent
    0.40
    a
    0.40
     Capture
    0.40
     Likes
    0.39
    POSITIVE LOGITS
    thebetter
    0.47
    foresaid
    0.45
     negeri
    0.45
    一樣
    0.44
     absur
    0.44
    jenis
    0.43
     bilmi
    0.42
     وہی
    0.41
     absurdity
    0.41
     worthless
    0.41
    Act Density 0.037%

    No Known Activations