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

    Neuronpedia

    INDEX
    Explanations

    website redirects/URLs/Login

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    之时
    -0.07
    _theta
    -0.07
    稍微
    -0.07
    _tok
    -0.06
     Know
    -0.06
    โย
    -0.06
    个体
    -0.06
     ↔
    -0.06
    まった
    -0.06
    ë
    -0.06
    POSITIVE LOGITS
    路由
    0.07
    Population
    0.07
    _pf
    0.07
    Policy
    0.07
    Cheap
    0.07
    startsWith
    0.07
    avigate
    0.06
     WAL
    0.06
    カラー
    0.06
     CONTROL
    0.06
    Act Density 0.014%

    No Known Activations