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

    Neuronpedia

    INDEX
    Explanations

    gifts, purpose, recipients

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <unused2221>
    0.42
     例如
    0.38
     происхождения
    0.38
     origin
    0.38
     geometrical
    0.36
     nucleotide
    0.36
    ofType
    0.36
    CLUSTERED
    0.35
    [][]
    0.34
    ClrType
    0.34
    POSITIVE LOGITS
     homeschool
    0.68
     homeschooling
    0.67
     подарок
    0.66
     Geschenk
    0.64
     गिफ्ट
    0.59
     untuk
    0.58
     для
    0.57
    孩子的
    0.57
     girlfriend
    0.57
     cadeau
    0.56
    Act Density 0.101%

    No Known Activations