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

    Neuronpedia

    INDEX
    Explanations

    references to family planning and gender dynamics

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

    "family" or "source" followed by a word related to planning or control

    np_acts-logits-general · gemini-2.0-flash

    family planning, source control

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     myſelf
    -1.02
     الحره
    -1.02
     theſe
    -0.97
     ſeveral
    -0.94
     ejus
    -0.94
     unſ
    -0.92
     itſelf
    -0.92
    RectangleBorder
    -0.90
     themſelves
    -0.89
    __":
    -0.88
    POSITIVE LOGITS
     h
    0.54
     bu
    0.54
     E
    0.52
     C
    0.50
     so
    0.48
     por
    0.48
     Start
    0.48
     
    0.47
     sou
    0.46
     truy
    0.46
    Act Density 0.643%

    No Known Activations