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

    Neuronpedia

    INDEX
    Explanations

    Code loops

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    used
    -0.07
    Day
    -0.07
     culture
    -0.07
     lui
    -0.06
     diligently
    -0.06
    Outcome
    -0.06
    /per
    -0.06
     fer
    -0.06
     Meyer
    -0.06
     altijd
    -0.06
    POSITIVE LOGITS
    -members
    0.07
     ауд
    0.06
     credibility
    0.06
    思想
    0.06
    ільки
    0.06
     dequeue
    0.06
     strán
    0.06
     створення
    0.06
    airy
    0.06
    ).(
    0.06
    Act Density 0.019%

    No Known Activations