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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash

    This neuron detects decimal numeric literals (floating-point numbers).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    還
    -0.06
    buttons
    -0.06
     self
    -0.06
     copied
    -0.06
    ابد
    -0.06
     plants
    -0.06
     lettuce
    -0.06
    シャル
    -0.06
    нод
    -0.06
    Steven
    -0.06
    POSITIVE LOGITS
    .const
    0.06
     Follow
    0.06
    ости
    0.06
     Чтобы
    0.06
    reader
    0.06
    ními
    0.06
     Papua
    0.06
     Giải
    0.06
    /proto
    0.06
       
    0.06
    Act Density 0.058%

    No Known Activations