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

    Neuronpedia

    INDEX
    Explanations

    comments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    iate
    -0.07
     dobr
    -0.07
    list
    -0.07
    thesize
    -0.06
    Rs
    -0.06
    agog
    -0.06
    fiction
    -0.06
     ECS
    -0.06
    urnal
    -0.06
    Info
    -0.06
    POSITIVE LOGITS
     لت
    0.07
     nộp
    0.07
    /question
    0.06
     sidelined
    0.06
    unitOfWork
    0.06
    	GUI
    0.06
     REFER
    0.06
    主要
    0.06
     KY
    0.06
     vyž
    0.06
    Act Density 0.023%

    No Known Activations