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

    Neuronpedia

    INDEX
    Explanations

    references to time, including the words "past," "present," and also relative descriptors like "new", or words suggestive of the passage of time like "life" or "smells"

    oai_token-act-pair · gemini-2.0-flash

    past

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    The
    -0.51
     noastre
    -0.47
    ığı
    -0.46
    A
    -0.46
     épa
    -0.43
    roskop
    -0.42
    THE
    -0.42
     wskaz
    -0.42
    He
    -0.42
    Whether
    -0.42
    POSITIVE LOGITS
    InjectAttribute
    1.07
     propOrder
    0.96
     مشين
    0.84
     CreateTagHelper
    0.83
     Meksiku
    0.76
     []:
    0.74
    VIAF
    0.74
    Hozzáférés
    0.73
     transférez
    0.71
    addCriterion
    0.71
    Act Density 1.068%

    No Known Activations