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

    Neuronpedia

    INDEX
    Explanations

    1

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ysql
    -0.07
    一件事情
    -0.07
    .Api
    -0.07
    _CRC
    -0.07
     swimming
    -0.07
     الخار
    -0.07
     Cul
    -0.06
    (query
    -0.06
    蹾
    -0.06
    _sdk
    -0.06
    POSITIVE LOGITS
    productive
    0.07
    grown
    0.07
     oo
    0.07
    workers
    0.07
    сет
    0.07
     nond
    0.06
    콕
    0.06
    反應
    0.06
    joined
    0.06
     correlate
    0.06
    Act Density 0.003%

    No Known Activations