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

    Neuronpedia

    INDEX
    Explanations

    references to government welfare programs and their impact

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

    Governmental assistance/welfare

    np_acts-logits-general · gemini-2.0-flash

    social welfare benefits

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     muun
    -0.35
    Lauren
    -0.33
     Lauren
    -0.33
     Polisi
    -0.31
     res
    -0.31
    ball
    -0.30
     encant
    -0.29
     싶
    -0.29
    0
    -0.29
     alrededores
    -0.29
    POSITIVE LOGITS
     ſche
    0.77
     faſt
    0.72
     Jefus
    0.72
     ſy
    0.68
     ſtate
    0.67
     propOrder
    0.67
     juſ
    0.66
     viſ
    0.66
     للاسماء
    0.66
     ſta
    0.65
    Act Density 0.302%

    No Known Activations