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

    Neuronpedia

    INDEX
    Explanations

    Berkeley

    np_max-act · gemini-2.0-flash

    The neuron specifically activates on occurrences of the proper-name “UC Berkeley.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    LCD
    -0.07
     tímto
    -0.07
    Mate
    -0.07
    tfoot
    -0.07
     dataList
    -0.07
     $("#"
    -0.07
     jsonArray
    -0.07
    Thomas
    -0.07
    .TabStop
    -0.06
     dakika
    -0.06
    POSITIVE LOGITS
     Berkeley
    0.08
     bo
    0.07
    ındır
    0.06
    طه
    0.06
     Anglic
    0.06
     сп
    0.06
    생활
    0.06
    луш
    0.06
    ERİ
    0.06
    하면서
    0.06
    Act Density 0.001%

    No Known Activations