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

    Neuronpedia

    INDEX
    Explanations

    numbers (multiples of 10/50)

    np_max-act · gemini-2.0-flash

    The main thing this neuron does is detect numeric measurements and quantity expressions (including decimal numbers and units).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    438
    -0.07
    emale
    -0.07
    Well
    -0.07
     sobre
    -0.07
    vary
    -0.06
    iram
    -0.06
     тела
    -0.06
    periences
    -0.06
    AIM
    -0.06
    rollment
    -0.06
    POSITIVE LOGITS
    َف
    0.06
    -bs
    0.06
     dart
    0.06
     đồ
    0.06
     dgv
    0.06
     ^^
    0.06
    .#
    0.06
     LONG
    0.06
    .rad
    0.06
    .'"↵↵
    0.06
    Act Density 0.031%

    No Known Activations