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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     balcony
    -0.06
    들도
    -0.06
    ']);↵
    -0.06
     creampie
    -0.06
    ılı
    -0.06
     "'";↵
    -0.06
     tyre
    -0.06
    ï
    -0.06
    <Resource
    -0.06
     sacrificed
    -0.06
    POSITIVE LOGITS
    uddenly
    0.06
     exclaimed
    0.06
     TICK
    0.06
    тиров
    0.06
    기에
    0.06
    .us
    0.06
    介绍
    0.05
    Xml
    0.05
     vend
    0.05
     supernatural
    0.05
    Act Density 0.024%

    No Known Activations