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

    Neuronpedia

    INDEX
    Explanations

    from

    np_max-act · gemini-2.0-flash

    The neuron activates on linker‐error trace lines indicating undefined references—specifically on the “referenced … from” parts of build errors.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    	IL
    -0.07
    _arc
    -0.07
    buyer
    -0.06
    ANO
    -0.06
     derail
    -0.06
    HeadersHeight
    -0.06
     MONEY
    -0.06
     territory
    -0.06
     cage
    -0.06
     Hyundai
    -0.06
    POSITIVE LOGITS
    Outlined
    0.07
    ++↵
    0.06
    &utm
    0.06
     =>↵
    0.06
    #from
    0.06
    ยวก
    0.06
     frustrating
    0.06
     ikt
    0.06
    capabilities
    0.06
    mons
    0.06
    Act Density 0.001%

    No Known Activations