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

    Neuronpedia

    INDEX
    Explanations

    code and academic papers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Hack
    -0.07
    ➷
    -0.07
    ﭔ
    -0.07
    冷链物流
    -0.07
     EVE
    -0.07
    reeNode
    -0.07
    振り
    -0.07
     walk
    -0.06
    极端
    -0.06
     '\''
    -0.06
    POSITIVE LOGITS
    occupation
    0.07
     가치
    0.07
    大切な
    0.06
    played
    0.06
    international
    0.06
     защиты
    0.06
    됩니다
    0.06
     kho
    0.06
    =__
    0.06
    か
    0.06
    Act Density 0.002%

    No Known Activations