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

    Neuronpedia

    INDEX
    Explanations

    mathematical formulas/code

    np_max-act · gemini-2.0-flash

    This neuron specializes in detecting highly precise floating-point numbers (long decimal numeric tokens).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    乌
    -0.06
     Mate
    -0.06
     bonuses
    -0.06
    堂
    -0.06
    ۲۲
    -0.06
    feb
    -0.06
     Raf
    -0.06
    ��
    -0.06
    quelle
    -0.06
     phí
    -0.06
    POSITIVE LOGITS
     ddl
    0.07
    .BackColor
    0.07
     Concurrent
    0.07
     instantiate
    0.07
     Wong
    0.07
    (feature
    0.07
    DMETHOD
    0.06
    @interface
    0.06
     denotes
    0.06
     Reported
    0.06
    Act Density 0.050%

    No Known Activations