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

    Neuronpedia

    INDEX
    Explanations

    references to familial relationships and citizenship eligibility

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

    children and family relationships

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    adaptiveStyles
    -0.44
     []:
    -0.40
    VYMaps
    -0.39
    bex
    -0.39
    udu
    -0.39
     Fac
    -0.38
    OLA
    -0.38
    vide
    -0.38
    jandro
    -0.38
    ROIT
    -0.36
    POSITIVE LOGITS
     dependents
    0.65
     children
    0.52
    GIVEREF
    0.51
    rungsseite
    0.48
     الحره
    0.48
     epidem
    0.48
     CHILDREN
    0.47
     family
    0.47
     dependent
    0.46
    transQ
    0.46
    Act Density 0.039%

    No Known Activations