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

    Neuronpedia

    INDEX
    Explanations

    chemicals

    np_max-act · gemini-2.0-flash

    discussions about safety and handling procedures for various chemical compounds.

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

    The neuron specializes in spotting fragments of systematic chemical compound names (IUPAC‐style nomenclature) within text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     potions
    -0.07
    ApplicationContext
    -0.06
     kế
    -0.06
    _REFER
    -0.06
    
    -0.06
    Calls
    -0.06
    φή
    -0.06
    허
    -0.06
    複
    -0.06
     신입
    -0.06
    POSITIVE LOGITS
     male
    0.07
     scrapped
    0.07
     unhealthy
    0.07
    /back
    0.07
     Protected
    0.06
    healthy
    0.06
    ازند
    0.06
     Southern
    0.06
    ΟΓ
    0.06
     developing
    0.06
    Act Density 0.025%

    No Known Activations