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

    Neuronpedia

    INDEX
    Explanations

    quotation marks/parentheses

    np_max-act · gemini-2.0-flash

    The neuron activates on floating‐point numeric literals (decimal numbers).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     UFC
    -0.06
     İli
    -0.06
    vůli
    -0.06
    _UD
    -0.06
    에도
    -0.06
     ملی
    -0.06
     Дмит
    -0.06
    �
    -0.06
    -table
    -0.06
    lines
    -0.06
    POSITIVE LOGITS
    Facebook
    0.07
    عب
    0.07
    。
    0.06
    (Socket
    0.06
     必
    0.06
     Chocolate
    0.06
    Byte
    0.06
    ασία
    0.06
    Remote
    0.06
     없어
    0.06
    Act Density 0.010%

    No Known Activations