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

    Neuronpedia

    INDEX
    Explanations

    references to family and family planning

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

    "family" followed by "planning"

    np_acts-logits-general · gemini-2.0-flash

    family planning

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AndEndTag
    -1.14
    يكب
    -0.64
    familien
    -0.58
    familie
    -0.57
    家族
    -0.56
    FailureListener
    -0.56
     الرياضيه
    -0.54
    @[+][
    -0.54
     Polis
    -0.54
    LikeLike
    -0.54
    POSITIVE LOGITS
     members
    1.03
     member
    0.85
     tree
    0.77
    members
    0.76
     unit
    0.74
     medlemmer
    0.73
     membres
    0.73
     miembros
    0.72
     MEMBERS
    0.70
     reunion
    0.70
    Act Density 0.075%

    No Known Activations