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

    Neuronpedia

    INDEX
    Explanations

    cloud

    np_max-act · gemini-2.0-flash

    The neuron strongly activates on the phrase “cloud-based,” i.e. it detects mentions of cloud-based platforms.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     games
    -0.07
    english
    -0.07
     oct
    -0.07
    ios
    -0.07
     attorney
    -0.07
     Tuesday
    -0.07
     institution
    -0.07
    ounsel
    -0.07
     song
    -0.07
     powered
    -0.07
    POSITIVE LOGITS
    typeparam
    0.08
    "]==
    0.07
    WORDS
    0.06
    __':↵
    0.06
    ><?=$
    0.06
     ctxt
    0.06
     cập
    0.06
     PropertyChanged
    0.06
    /lic
    0.06
    izontally
    0.06
    Act Density 0.008%

    No Known Activations