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

    Neuronpedia

    INDEX
    Explanations

    patent descriptions

    np_max-act · gemini-2.0-flash

    The neuron detects generalizing or hedging adverbs and phrases (e.g. “typically,” “commonly,” “usually”) that introduce broad, non‐specific descriptions.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     diary
    -0.07
     inse
    -0.07
    -focus
    -0.07
    imb
    -0.06
    -tracking
    -0.06
    edir
    -0.06
    ického
    -0.06
    oku
    -0.06
    (x
    -0.06
    urls
    -0.06
    POSITIVE LOGITS
    .ADMIN
    0.06
     Investment
    0.06
    799
    0.06
    Watcher
    0.06
    Trade
    0.06
    arkers
    0.06
    Selectable
    0.06
    Available
    0.06
    _IDENT
    0.06
     Appears
    0.06
    Act Density 0.070%

    No Known Activations