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

    Neuronpedia

    INDEX
    Explanations

    day and temporal phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Dig
    0.49
    Hoe
    0.44
    Tree
    0.44
     draw
    0.42
     aid
    0.41
    树
    0.41
     Bola
    0.41
     moment
    0.39
    Frequently
    0.39
     equalize
    0.39
    POSITIVE LOGITS
     féri
    0.69
    OfWeek
    0.66
    dreams
    0.66
    tona
    0.59
    曜日
    0.56
     háb
    0.53
    night
    0.53
    OfMonth
    0.53
    day
    0.52
    dream
    0.52
    Act Density 0.035%

    No Known Activations