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

    Neuronpedia

    INDEX
    Explanations

    commercial transactions

    np_max-act · gemini-2.0-flash

    The neuron selectively activates on numeric tokens—especially numbers, percentages, and decimal values—in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    appear
    -0.07
    953
    -0.07
    Ar
    -0.07
    ev
    -0.06
     chemotherapy
    -0.06
    Ray
    -0.06
     �
    -0.06
     tomatoes
    -0.06
     JD
    -0.06
    figures
    -0.06
    POSITIVE LOGITS
     радян
    0.07
    λης
    0.07
    *.
    0.07
     знаход
    0.06
    _peng
    0.06
     अपन
    0.06
    )?↵↵
    0.06
    \Message
    0.06
     تف
    0.06
     velocidad
    0.06
    Act Density 0.028%

    No Known Activations