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

    Neuronpedia

    INDEX
    Explanations

    News reports

    np_max-act · gemini-2.0-flash

    The main thing this neuron does is detect numeric tokens and numerical expressions (e.g., years, measurements, currency amounts, and other digit‐based values).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     погляд
    -0.07
    ecessary
    -0.07
     keypad
    -0.06
    .Linear
    -0.06
    \Api
    -0.06
    elve
    -0.06
     quirky
    -0.06
     Law
    -0.06
     RANGE
    -0.06
    Wins
    -0.06
    POSITIVE LOGITS
    ishlist
    0.06
    �
    0.06
     '::
    0.06
    cou
    0.06
     ViewBag
    0.06
    .ALIGN
    0.06
    :'.$
    0.06
    .course
    0.06
     pne
    0.06
    SingleOrDefault
    0.06
    Act Density 0.380%

    No Known Activations