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
     hosts
    -0.07
     Somerset
    -0.07
     Augusta
    -0.07
     favored
    -0.07
    _OBJ
    -0.07
    .examples
    -0.06
    改变了
    -0.06
    冰冷
    -0.06
     unset
    -0.06
    .result
    -0.06
    POSITIVE LOGITS
     spl
    0.07
     четы
    0.07
     typography
    0.07
     BeautifulSoup
    0.07
    (float
    0.07
    (gca
    0.07
    asticsearch
    0.07
     chute
    0.06
    \b
    0.06
    ,np
    0.06
    Act Density 0.001%

    No Known Activations