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

    Neuronpedia

    INDEX
    Explanations

    .

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <DateTime
    -0.07
    274
    -0.06
    (android
    -0.06
    )view
    -0.06
    iks
    -0.06
     Slayer
    -0.06
     얻
    -0.06
    幸福
    -0.06
     supplies
    -0.06
     chosen
    -0.06
    POSITIVE LOGITS
    Yeah
    0.07
    ỳ
    0.07
    =",
    0.06
     této
    0.06
     Celebration
    0.06
    ivatel
    0.06
    FLOW
    0.06
    řít
    0.06
    В
    0.06
     SCH
    0.06
    Act Density 0.187%

    No Known Activations