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

    Neuronpedia

    INDEX
    Explanations

    light

    np_max-act · gemini-2.0-flash

    the neuron is triggered by floating-point numeric values (decimal measurements) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Ending
    -0.07
    ,nil
    -0.07
     Mand
    -0.07
     twisted
    -0.07
    _argument
    -0.06
    licer
    -0.06
    Element
    -0.06
    loader
    -0.06
     Ending
    -0.06
     pathlib
    -0.06
    POSITIVE LOGITS
    0.07
    Ы
    0.07
    (bind
    0.07
    -bodied
    0.06
    >--
    0.06
     airy
    0.06
    (prom
    0.06
    /ml
    0.06
    (max
    0.06
     Sports
    0.06
    Act Density 0.001%

    No Known Activations