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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash

    The neuron is primarily detecting numerical measurements (especially decimal numbers) such as doses, concentrations, and other quantitative values in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    yclopedia
    -0.07
    ,System
    -0.07
    (mappedBy
    -0.07
     semiclassical
    -0.07
    세요
    -0.07
     undermining
    -0.07
     갤로그
    -0.07
     Britann
    -0.06
     catastrophe
    -0.06
    ArgumentException
    -0.06
    POSITIVE LOGITS
     PCM
    0.07
     PR
    0.07
    eka
    0.07
     Documents
    0.06
    副
    0.06
    DL
    0.06
     PAC
    0.06
    斗
    0.06
    ्ण
    0.06
    �
    0.06
    Act Density 0.034%

    No Known Activations