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

    Neuronpedia

    INDEX
    Explanations

    benefits

    np_max-act · gemini-2.0-flash

    The neuron fires on mentions of insurance/disability benefit applications and related numeric references (e.g., “benefits,” “insurance,” dates, section numbers).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    History
    -0.07
    Taken
    -0.06
     صح
    -0.06
    Over
    -0.06
    Short
    -0.06
    ạ
    -0.06
    Estado
    -0.06
    Close
    -0.06
    اها
    -0.06
     colonies
    -0.06
    POSITIVE LOGITS
     haystack
    0.07
    .super
    0.06
     aylık
    0.06
     režim
    0.06
    bjerg
    0.06
    ناد
    0.06
    ême
    0.06
    intersect
    0.06
     плит
    0.06
    igmat
    0.06
    Act Density 0.005%

    No Known Activations