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

    Neuronpedia

    INDEX
    Explanations

    File sharing/uploading

    np_max-act · gemini-2.0-flash

    The neuron lights up on words in instructions or requests about providing, sending, uploading, or sharing a file or image.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ISHED
    -0.07
    ungen
    -0.07
    _plugins
    -0.07
    uli
    -0.07
    øy
    -0.07
    duğu
    -0.06
     тур
    -0.06
    acht
    -0.06
    ISE
    -0.06
    ít
    -0.06
    POSITIVE LOGITS
     imperative
    0.08
    className
    0.07
     yalnız
    0.07
     населения
    0.06
    clide
    0.06
     viewModel
    0.06
    �
    0.06
    .DAO
    0.06
    년도
    0.06
     Gotham
    0.06
    Act Density 0.018%

    No Known Activations