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

    Neuronpedia

    INDEX
    Explanations

    Stanford

    np_max-act · gemini-2.0-flash

    The neuron detects mentions of academic institutions, especially university names.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     sớm
    -0.06
    	Long
    -0.06
    \Message
    -0.06
     Minuten
    -0.06
    ocalypse
    -0.06
     parametro
    -0.06
     contrato
    -0.06
    ONGL
    -0.06
    響
    -0.06
     ткани
    -0.06
    POSITIVE LOGITS
     Stanford
    0.09
     University
    0.09
     Rutgers
    0.08
     BYU
    0.08
     Baylor
    0.08
     Cornell
    0.08
    /MIT
    0.07
     Lilly
    0.07
     Hopkins
    0.07
     Univ
    0.07
    Act Density 0.025%

    No Known Activations