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

    Neuronpedia

    INDEX
    Explanations

    positive performance descriptions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    醵
    -0.08
     Logged
    -0.07
     Page
    -0.07
    .Bool
    -0.07
     doom
    -0.06
     Nero
    -0.06
     Account
    -0.06
     Further
    -0.06
     doPost
    -0.06
    舆
    -0.06
    POSITIVE LOGITS
    ابل
    0.07
    华丽
    0.07
    往返
    0.07
    宿迁
    0.07
    _walk
    0.07
    多年来
    0.07
    潍坊
    0.07
     Cedar
    0.07
    宛
    0.07
    Hands
    0.07
    Act Density 0.048%

    No Known Activations