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

    Neuronpedia

    INDEX
    Explanations

    parentheses

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Dating
    -0.07
    valid
    -0.07
     Different
    -0.07
    Handling
    -0.07
     hookers
    -0.07
     certain
    -0.07
    ",__
    -0.07
    获得更多
    -0.07
    סמוך
    -0.06
    无数次
    -0.06
    POSITIVE LOGITS
    pcm
    0.07
     fled
    0.07
     mieszka
    0.06
     giám
    0.06
    ッド
    0.06
    农产品
    0.06
     */;↵
    0.06
    ′
    0.06
    促进
    0.06
     يت
    0.06
    Act Density 0.005%

    No Known Activations