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

    Neuronpedia

    INDEX
    Explanations

    warranties

    np_max-act · gemini-2.0-flash

    The neuron fires on the term “WARRANTIES,” i.e. occurrences of that specific word in text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .lt
    -0.07
    _square
    -0.07
    PointerException
    -0.07
     cracking
    -0.07
    شنامه
    -0.06
    -ing
    -0.06
    imleri
    -0.06
    roje
    -0.06
     E
    -0.06
     fifo
    -0.06
    POSITIVE LOGITS
     visually
    0.07
    고
    0.06
    엘
    0.06
     quiere
    0.06
     previews
    0.06
     Codable
    0.06
     يمكن
    0.06
     redefine
    0.06
     petites
    0.06
     esp
    0.06
    Act Density 0.001%

    No Known Activations