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

    Neuronpedia

    INDEX
    Explanations

    Forms of "to be"

    np_max-act · gemini-2.0-flash

    The neuron never activates—it doesn’t detect any pattern or feature in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    IODevice
    -0.07
     ups
    -0.07
    Decoration
    -0.07
     zakáz
    -0.07
    Lifetime
    -0.06
    불
    -0.06
    增
    -0.06
     staat
    -0.06
    Bookmark
    -0.06
     sucess
    -0.06
    POSITIVE LOGITS
    .full
    0.07
    )--
    0.07
    ictionary
    0.07
     strom
    0.06
     goodwill
    0.06
    519
    0.06
     vue
    0.06
    Copying
    0.06
    softmax
    0.06
    urname
    0.06
    Act Density 0.028%

    No Known Activations