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

    Neuronpedia

    INDEX
    Explanations

    data identifiers

    np_max-act · gemini-2.0-flash

    The neuron activates on numeric tokens containing decimal points, i.e. floating-point numbers.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Ан
    -0.07
    ฟ
    -0.07
    仍
    -0.06
    igrams
    -0.06
    овани
    -0.06
     '{@
    -0.06
    /Sh
    -0.06
    	md
    -0.06
    Knight
    -0.06
    що
    -0.06
    POSITIVE LOGITS
    -road
    0.06
    _targets
    0.06
    _LIBRARY
    0.06
     RX
    0.06
    _RESERVED
    0.06
     tumor
    0.06
    JSON
    0.06
     yatırım
    0.06
    ===========↵
    0.06
    ResultSet
    0.06
    Act Density 0.012%

    No Known Activations