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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash

    terms related to health risks and conditions associated with tobacco and smoking.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron selectively activates on the conjunction “and.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     bitch
    -0.07
     roses
    -0.07
     Augusta
    -0.07
    .SelectSingleNode
    -0.07
     discovers
    -0.06
     rum
    -0.06
     韓
    -0.06
     течение
    -0.06
     labeling
    -0.06
     Mention
    -0.06
    POSITIVE LOGITS
    ुद
    0.07
    ,&
    0.06
     setTime
    0.06
    iect
    0.06
    альным
    0.06
     carro
    0.06
     मस
    0.06
    panion
    0.06
    _WEEK
    0.06
    тор
    0.05
    Act Density 0.066%

    No Known Activations