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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash

    The neuron is tuned to detect quantitative terms and numeric references—especially fractional or scaled amounts in discussions of voting or scoring.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    983
    -0.07
    кові
    -0.07
    ema
    -0.07
     наказ
    -0.07
     Susan
    -0.07
     Rico
    -0.06
     Koh
    -0.06
     CrossRef
    -0.06
     Bry
    -0.06
    _temperature
    -0.06
    POSITIVE LOGITS
     silhouette
    0.06
    ывать
    0.06
    functions
    0.06
     bursts
    0.06
    れた
    0.06
    ”?
    0.06
    nost
    0.06
    лл
    0.06
    itics
    0.06
    ehicles
    0.06
    Act Density 0.083%

    No Known Activations