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

    Neuronpedia

    INDEX
    Explanations

    word character

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Global
    -0.08
    อำนวย
    -0.08
     cấp
    -0.07
    ovy
    -0.07
     Advanced
    -0.07
     Domestic
    -0.07
     forced
    -0.07
     Bachelor
    -0.07
     invention
    -0.07
     Licensed
    -0.07
    POSITIVE LOGITS
    的地图
    0.08
    ✒
    0.07
    LIK
    0.07
    etxt
    0.07
    dde
    0.07
    كه
    0.07
    욱
    0.07
    ически
    0.07
    的缘
    0.07
     dislike
    0.07
    Act Density 0.007%

    No Known Activations