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

    Neuronpedia

    INDEX
    Explanations

    source code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ávky
    -0.08
     vic
    -0.07
    ého
    -0.07
     meaning
    -0.07
     svém
    -0.07
    재
    -0.07
    จะ
    -0.06
     kiếm
    -0.06
     sewing
    -0.06
     주문
    -0.06
    POSITIVE LOGITS
    .JsonProperty
    0.07
     synd
    0.06
    (rowIndex
    0.06
     MutableLiveData
    0.06
    081
    0.06
    /pages
    0.06
     Лит
    0.06
    roomId
    0.06
    418
    0.06
    rien
    0.06
    Act Density 0.014%

    No Known Activations