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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    смер
    -0.08
    وذ
    -0.07
    -context
    -0.07
    kus
    -0.07
     appellant
    -0.07
    ilig
    -0.06
    isRequired
    -0.06
    elage
    -0.06
    翼
    -0.06
    LOGGER
    -0.06
    POSITIVE LOGITS
    したら
    0.07
     Emp
    0.07
    𝕻
    0.07
     Ghana
    0.07
    ファ
    0.07
    邀
    0.07
     Ve
    0.07
    鹊
    0.07
    加重
    0.07
    acement
    0.07
    Act Density 0.001%

    No Known Activations