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

    Neuronpedia

    INDEX
    Explanations

    descriptions

    np_max-act · gemini-2.0-flash

    The neuron fires on nouns naming products, services, or other item categories.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    object
    -0.07
    Digits
    -0.07
     origins
    -0.06
     acquainted
    -0.06
    ResourceManager
    -0.06
    CursorPosition
    -0.06
    dataset
    -0.06
    .descriptor
    -0.06
    SError
    -0.06
    deadline
    -0.06
    POSITIVE LOGITS
    işi
    0.06
    oseconds
    0.06
    736
    0.06
    吴
    0.06
     WTF
    0.06
    ópez
    0.06
     $('.
    0.06
     LB
    0.06
    픈
    0.06
     ΔΗΜ
    0.06
    Act Density 0.431%

    No Known Activations