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

    Neuronpedia

    INDEX
    Explanations

    weight

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    reve
    -0.07
     promotional
    -0.07
    �
    -0.07
    汲取
    -0.07
     Embed
    -0.07
    /code
    -0.06
     puedes
    -0.06
    弯曲
    -0.06
     judges
    -0.06
     appealed
    -0.06
    POSITIVE LOGITS
    秋
    0.07
    Watcher
    0.07
    心情
    0.07
    فص
    0.07
    	total
    0.07
     Vũ
    0.06
    ._
    0.06
    Hidden
    0.06
     founder
    0.06
    ائهم
    0.06
    Act Density 0.019%

    No Known Activations