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

    Neuronpedia

    INDEX
    Explanations

    math symbols

    np_max-act · gemini-2.0-flash

    This neuron activates on floating-point numeric literals (numbers with decimal points and fractional parts).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    }-${
    -0.07
    mint
    -0.07
    _extent
    -0.07
    acoes
    -0.07
     mediation
    -0.06
    itra
    -0.06
    epam
    -0.06
    geist
    -0.06
     setAddress
    -0.06
    .med
    -0.06
    POSITIVE LOGITS
    _CYCLE
    0.07
    シー
    0.06
     REC
    0.06
    وية
    0.06
    olo
    0.06
     t�
    0.06
    ー�
    0.06
     بیماری
    0.06
    �
    0.06
     GLsizei
    0.05
    Act Density 0.004%

    No Known Activations