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

    Neuronpedia

    INDEX
    Explanations

    exacerb

    np_max-act · gemini-2.0-flash

    The neuron activates on the root “exacerb” (as in “exacerbation” or “exacerbations”), i.e. mentions of acute worsening events.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ाद
    -0.07
    ीर
    -0.06
     shortages
    -0.06
     �
    -0.06
    ‌پ
    -0.06
    _attachment
    -0.06
    		    ↵
    -0.06
     стандарт
    -0.06
    reme
    -0.06
     inte
    -0.06
    POSITIVE LOGITS
    _bonus
    0.08
     exacerb
    0.07
    .lex
    0.07
    -txt
    0.06
    jr
    0.06
     récup
    0.06
     bloque
    0.06
     تخصصی
    0.06
    (?:
    0.06
     fresh
    0.06
    Act Density 0.007%

    No Known Activations