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

    Neuronpedia

    INDEX
    Explanations

    shows

    np_max-act · gemini-2.0-flash

    The neuron primarily activates on plural nouns (words ending in “–s” or similar plural forms).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     етап
    -0.07
    询
    -0.06
     реж
    -0.06
     полі
    -0.06
     яка
    -0.06
    ذكر
    -0.06
    ир
    -0.06
     catering
    -0.06
    -La
    -0.06
    ApiKey
    -0.06
    POSITIVE LOGITS
     enhance
    0.07
    'am
    0.07
    unfold
    0.06
    ’am
    0.06
    �
    0.06
     QName
    0.06
    pei
    0.06
    .her
    0.06
     plumbing
    0.06
     mobs
    0.06
    Act Density 0.111%

    No Known Activations