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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    这片
    -0.07
    拈
    -0.07
    在于
    -0.07
    increments
    -0.06
    掌门
    -0.06
     spelled
    -0.06
     nối
    -0.06
     dressed
    -0.06
    绽
    -0.06
    oner
    -0.06
    POSITIVE LOGITS
    _G
    0.07
    _area
    0.07
    _con
    0.07
    物业管理
    0.06
    odge
    0.06
     Hay
    0.06
     Shanghai
    0.06
    ,var
    0.06
    ,,,
    0.06
    倒塌
    0.06
    Act Density 0.075%

    No Known Activations