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

    Neuronpedia

    INDEX
    Explanations

    Quotation marks

    np_max-act · gemini-2.0-flash

    The neuron fires on numeric literals—especially decimal numbers—indicating it’s looking for floating-point values.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     dend
    -0.07
     Mets
    -0.07
    知识
    -0.07
     blends
    -0.07
     control
    -0.06
    loy
    -0.06
    と
    -0.06
     stere
    -0.06
     возраста
    -0.06
     leadership
    -0.06
    POSITIVE LOGITS
    .getElement
    0.07
    .Pe
    0.07
     surname
    0.06
    Min
    0.06
     budeme
    0.06
    ヤ
    0.06
    salary
    0.06
     manage
    0.06
    420
    0.06
    ome
    0.06
    Act Density 0.004%

    No Known Activations