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

    Neuronpedia

    INDEX
    Explanations

    carry

    np_max-act · gemini-2.0-flash

    The neuron activates on mentions of a “carry” or “carry flag” in arithmetic or bitwise addition contexts.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    私は
    -0.07
     Comics
    -0.07
    	RTLR
    -0.06
    (Print
    -0.06
     Pages
    -0.06
     userType
    -0.06
    autoreleasepool
    -0.06
    653
    -0.06
     headset
    -0.06
    ±ط
    -0.06
    POSITIVE LOGITS
     resultado
    0.08
     Drugs
    0.07
     pars
    0.07
     traj
    0.06
     natuur
    0.06
    lua
    0.06
    kers
    0.06
    aju
    0.06
    ají
    0.06
     chức
    0.06
    Act Density 0.002%

    No Known Activations