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

    Neuronpedia

    INDEX
    Explanations

    hour

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     isAuthenticated
    -0.07
    喜欢吃
    -0.07
    .prepareStatement
    -0.07
    炸
    -0.07
     FactoryGirl
    -0.07
    -dismissible
    -0.07
     cpf
    -0.07
    脑子里
    -0.06
    しばらく
    -0.06
    ADDING
    -0.06
    POSITIVE LOGITS
     exhaust
    0.08
    enchmark
    0.07
     talent
    0.07
    Listing
    0.07
     stool
    0.07
    LOUD
    0.07
     SHOW
    0.07
     البط
    0.07
     lineage
    0.07
     lithium
    0.06
    Act Density 0.001%

    No Known Activations