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

    Neuronpedia

    INDEX
    Explanations

    protecting

    np_max-act · gemini-2.0-flash

    The neuron is sensitive to mentions of patent protection and related IP terms.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     whereabouts
    -0.06
    icans
    -0.06
    messages
    -0.06
    Delegate
    -0.06
     forgiving
    -0.06
    іх
    -0.05
     yes
    -0.05
    .xlabel
    -0.05
    城市
    -0.05
     MPs
    -0.05
    POSITIVE LOGITS
    (prediction
    0.07
     bíl
    0.07
    ===========↵
    0.06
     Osc
    0.06
    BMW
    0.06
     Vector
    0.06
    _RECE
    0.06
    ーバ
    0.06
    omi
    0.06
     zih
    0.06
    Act Density 0.211%

    No Known Activations