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

    Neuronpedia

    INDEX
    Explanations

    coding questions

    np_max-act · gemini-2.0-flash

    The neuron selectively activates on numeric literals with decimal points (floating‐point numbers) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Below
    -0.07
    (Order
    -0.07
    arlo
    -0.07
    인이
    -0.07
     Below
    -0.06
     relates
    -0.06
     assertNull
    -0.06
    .xyz
    -0.06
     followers
    -0.06
     Erg
    -0.06
    POSITIVE LOGITS
    -document
    0.07
     Пер
    0.06
     Maced
    0.06
     snapshot
    0.06
    破
    0.06
    �
    0.06
    μμα
    0.06
    急
    0.06
    -commercial
    0.06
     |↵
    0.06
    Act Density 0.023%

    No Known Activations