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

    Neuronpedia

    INDEX
    Explanations

    below

    np_max-act · gemini-2.0-flash

    The neuron activates on mentions of populations “below the poverty line,” i.e. phrases indicating percentages living in poverty.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    optic
    -0.07
    리아
    -0.07
     posters
    -0.07
    	REQUIRE
    -0.07
     pit
    -0.06
    ुभ
    -0.06
    Ι
    -0.06
     thinkers
    -0.06
     hosted
    -0.06
    er
    -0.06
    POSITIVE LOGITS
     lasc
    0.06
    :black
    0.06
     excessive
    0.06
    вав
    0.06
    ými
    0.06
     wonderfully
    0.06
     клас
    0.06
     contempt
    0.06
     nonprofit
    0.06
     bian
    0.06
    Act Density 0.000%

    No Known Activations