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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash

    The neuron activates on numeric tokens representing precise statistical values—especially decimal numbers used in confidence intervals, p-values, and odds ratios.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ANN
    -0.07
     Arrays
    -0.07
     Kids
    -0.07
    Ю
    -0.07
    AG
    -0.07
    Require
    -0.06
    According
    -0.06
     Cann
    -0.06
     recurs
    -0.06
    “A
    -0.06
    POSITIVE LOGITS
    .BorderSize
    0.06
     �
    0.06
     Peel
    0.06
     χρησιμοποι
    0.06
    스의
    0.06
     mins
    0.06
    صت
    0.06
    ...↵↵
    0.06
    	class
    0.06
     článku
    0.06
    Act Density 0.003%

    No Known Activations