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

    Neuronpedia

    INDEX
    Explanations

    references to individuals and their relationships to others

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

    "His" followed by a noun

    np_acts-logits-general · gemini-2.0-flash

    his and their possessions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    IUrlHelper
    -0.61
    ViewFeatures
    -0.59
    人了
    -0.53
    Polecam
    -0.53
     respecte
    -0.51
    Gruß
    -0.50
     respectivamente
    -0.49
    Personensuche
    -0.49
    Referències
    -0.48
     respectively
    -0.46
    POSITIVE LOGITS
     goal
    0.67
    目的是
    0.67
    HasForeignKey
    0.65
     parents
    0.63
     concern
    0.62
     aim
    0.59
    确
    0.58
     مشين
    0.58
    jstor
    0.56
    ódó
    0.56
    Act Density 0.229%

    No Known Activations