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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash

    The neuron activates on four-digit year numbers (and year ranges) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    629
    -0.06
     стандарт
    -0.06
     mines
    -0.06
    parcel
    -0.06
     Alpha
    -0.06
    ATA
    -0.06
     تکن
    -0.06
     стил
    -0.06
     chloride
    -0.05
     HID
    -0.05
    POSITIVE LOGITS
    Edited
    0.08
     पड़
    0.07
    مم
    0.07
    LATED
    0.07
    sgi
    0.07
    姆
    0.06
     цей
    0.06
     {{--<
    0.06
    (tasks
    0.06
    	layout
    0.06
    Act Density 0.007%

    No Known Activations