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

    Neuronpedia

    INDEX
    Explanations

    feed

    np_max-act · gemini-2.0-flash

    The neuron primarily activates on occurrences of “RSS” or “feed” (and their variants), i.e. references to web feeds.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     DRIVER
    -0.07
     fsm
    -0.07
    ادث
    -0.07
    .left
    -0.06
    _generic
    -0.06
    Match
    -0.06
    δ
    -0.06
    _LOOK
    -0.06
    ERM
    -0.06
    issors
    -0.06
    POSITIVE LOGITS
     tert
    0.07
     сбор
    0.07
    َج
    0.06
    -feed
    0.06
    _hz
    0.06
    byt
    0.06
     smě
    0.06
     lidi
    0.06
     exports
    0.06
    Contacts
    0.06
    Act Density 0.009%

    No Known Activations