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

    Neuronpedia

    INDEX
    Explanations

    comparisons and combinations

    np_max-act · gemini-2.0-flash

    The neuron fires on tokens signaling a direct comparison or contrast—especially “vs.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    YPES
    -0.07
    Trump
    -0.06
     systems
    -0.06
     pis
    -0.06
     markets
    -0.06
    áno
    -0.06
    	statement
    -0.06
    (instruction
    -0.06
     trader
    -0.06
     organizational
    -0.06
    POSITIVE LOGITS
    دارة
    0.07
    MEDIA
    0.07
    oretical
    0.06
     resulted
    0.06
    .touch
    0.06
    _locale
    0.06
    олн
    0.06
    确
    0.06
    irut
    0.06
    kovou
    0.06
    Act Density 0.219%

    No Known Activations