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

    Neuronpedia

    INDEX
    Explanations

    complete

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of marking tasks or items as “complete,” i.e. references to completing or checking off an item.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     θ
    -0.07
    َر
    -0.06
     Singer
    -0.06
    储
    -0.06
     HDD
    -0.06
    /mainwindow
    -0.06
    _UNIT
    -0.06
    .DOM
    -0.06
     rm
    -0.06
    _age
    -0.06
    POSITIVE LOGITS
     Presented
    0.06
    .redis
    0.06
    	tab
    0.06
    Public
    0.06
     vem
    0.06
    IOD
    0.06
     paran
    0.06
    ています
    0.06
    lag
    0.06
     chlap
    0.06
    Act Density 0.035%

    No Known Activations