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
    ently
    -0.07
    .EVT
    -0.07
    軽
    -0.06
     toplum
    -0.06
    .cycle
    -0.06
     Sam
    -0.06
     portfolio
    -0.06
    ансов
    -0.06
     Discover
    -0.06
    收入
    -0.06
    POSITIVE LOGITS
     anarchists
    0.06
    issional
    0.06
     Halifax
    0.06
    .Categories
    0.06
     ((!
    0.06
     Seznam
    0.06
     Phillies
    0.06
     cram
    0.06
     공부
    0.06
    llib
    0.06
    Act Density 0.003%

    No Known Activations