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

    Neuronpedia

    INDEX
    Explanations

    older

    np_max-act · gemini-2.0-flash

    The neuron fires on numeric data tokens—especially decimal fractions and percentages—in demographic/statistical passages.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    markup
    -0.07
     Parade
    -0.07
    -region
    -0.06
     erfol
    -0.06
    _timeout
    -0.06
    १�
    -0.06
    ión
    -0.06
     suicidal
    -0.06
     cz
    -0.06
     داخ
    -0.06
    POSITIVE LOGITS
    "})↵
    0.07
     transparency
    0.07
    Hands
    0.06
     Future
    0.06
    ()))↵
    0.06
    Products
    0.06
     weaponry
    0.06
    Fore
    0.06
     Numbers
    0.06
    perc
    0.06
    Act Density 0.001%

    No Known Activations