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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash

    The neuron activates on plural, countable nouns that follow or accompany numerical quantities.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    -third
    -0.07
    .rooms
    -0.07
    .Builder
    -0.07
    "There
    -0.07
    “It
    -0.07
     behaves
    -0.06
    “There
    -0.06
    .CONT
    -0.06
     (%
    -0.06
     downstream
    -0.06
    POSITIVE LOGITS
    <GameObject
    0.06
    NES
    0.06
    .ObjectId
    0.06
     Honest
    0.06
    대
    0.06
    añ
    0.06
    Graphics
    0.06
     unique
    0.06
    Ў
    0.06
     countless
    0.06
    Act Density 0.014%

    No Known Activations