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

    Neuronpedia

    INDEX
    Explanations

    height

    np_max-act · gemini-2.0-flash

    This neuron detects numeric measurements or dimensional specifications (e.g. heights, clearances) in technical descriptions.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     MOR
    -0.07
     Qur
    -0.06
     reels
    -0.06
    aled
    -0.06
    .Since
    -0.06
    Ol
    -0.06
    errer
    -0.06
    lech
    -0.06
     begr
    -0.06
    ceries
    -0.05
    POSITIVE LOGITS
    商品
    0.07
    로드
    0.07
    rapy
    0.07
     adjustable
    0.07
     -(
    0.07
    +'/'+
    0.07
    .Sub
    0.07
     TForm
    0.07
    _associ
    0.07
    _sub
    0.07
    Act Density 0.019%

    No Known Activations