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

    Neuronpedia

    INDEX
    Explanations

    organization

    np_max-act · gemini-2.0-flash

    references to the organization and training background of a language model.

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

    This neuron detects the occurrence of the token “Organization” (i.e. mentions of that specific named institution).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    BEST
    -0.06
    Grand
    -0.06
    	LCD
    -0.06
    .Android
    -0.06
    IE
    -0.06
    _projection
    -0.06
     Nation
    -0.06
    AntiForgeryToken
    -0.06
    áč
    -0.06
     cannons
    -0.06
    POSITIVE LOGITS
     perpetrated
    0.07
    RegExp
    0.07
    nesota
    0.07
    _declaration
    0.07
     Alibaba
    0.07
     setOpen
    0.07
     obsess
    0.06
     ödem
    0.06
     První
    0.06
    /*/
    0.06
    Act Density 0.001%

    No Known Activations