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

    Neuronpedia

    INDEX
    Explanations

    Different languages

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -section
    -0.07
    surface
    -0.06
    /display
    -0.06
    agents
    -0.06
     extract
    -0.06
    ruit
    -0.06
    _wait
    -0.06
     temperatures
    -0.06
     Trait
    -0.06
    burn
    -0.06
    POSITIVE LOGITS
    Danny
    0.07
     PropertyChangedEventArgs
    0.07
    (animated
    0.06
     eş
    0.06
     Россий
    0.06
     Megan
    0.06
     här
    0.06
     herald
    0.06
     kê
    0.06
    (dev
    0.06
    Act Density 0.066%

    No Known Activations