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

    Neuronpedia

    INDEX
    Explanations

    death

    np_max-act · gemini-2.0-flash

    The neuron activates on words about capital punishment—especially “execute,” “death,” and “penalty.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    iating
    -0.06
     Brooklyn
    -0.06
     Jade
    -0.06
    Stride
    -0.06
     مسائل
    -0.06
     Tampa
    -0.06
     труб
    -0.06
    석
    -0.06
    ุณ
    -0.06
     kidneys
    -0.06
    POSITIVE LOGITS
    cription
    0.07
     hearty
    0.07
    yet
    0.07
    stuff
    0.06
     Чтобы
    0.06
    	then
    0.06
    är
    0.06
     town
    0.06
     "<?
    0.06
    cdr
    0.06
    Act Density 0.001%

    No Known Activations