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

    Neuronpedia

    INDEX
    Explanations

    Border crossings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     implode
    -0.08
    续航
    -0.07
    (period
    -0.07
    蚀
    -0.07
     Worth
    -0.07
     Albums
    -0.07
    .Second
    -0.07
     ?,
    -0.07
     Victor
    -0.07
     Either
    -0.07
    POSITIVE LOGITS
    的需求
    0.07
    ᚱ
    0.07
     niño
    0.07
    -based
    0.07
     investigación
    0.07
    生产的
    0.06
    ﺮ
    0.06
    秧
    0.06
     Mur
    0.06
     científico
    0.06
    Act Density 0.022%

    No Known Activations