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

    Neuronpedia

    INDEX
    Explanations

    minimum

    np_max-act · gemini-2.0-flash

    The neuron activates on mentions of getting stuck in a “local minimum” during optimization.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     shipping
    -0.06
     beverage
    -0.06
     respect
    -0.06
     manage
    -0.06
    ('');↵↵
    -0.06
    _banner
    -0.06
    乱
    -0.06
     boot
    -0.06
    .Pattern
    -0.06
     Pence
    -0.06
    POSITIVE LOGITS
    MODEL
    0.07
     checkBox
    0.06
    duğu
    0.06
     �
    0.06
     wäh
    0.06
     (){↵
    0.06
     QMainWindow
    0.06
    ocus
    0.06
    apolis
    0.06
    ，都
    0.06
    Act Density 0.005%

    No Known Activations