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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Stacy
    -0.07
    _Project
    -0.07
     through
    -0.07
     Hank
    -0.07
     Proper
    -0.07
     Hundreds
    -0.07
    人民
    -0.07
     stripped
    -0.07
     revolution
    -0.07
     Revolution
    -0.07
    POSITIVE LOGITS
     लगभग
    0.07
    -être
    0.07
     onView
    0.07
    Раз
    0.06
     увагу
    0.06
    )`↵
    0.06
    forder
    0.06
    �
    0.06
     왜
    0.06
    ウ
    0.06
    Act Density 0.020%

    No Known Activations