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

    Neuronpedia

    INDEX
    Explanations

    scientific introductions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    fest
    -0.07
    dup
    -0.06
     poetry
    -0.06
     масло
    -0.06
    dr
    -0.06
     pict
    -0.06
    elim
    -0.06
    	wc
    -0.06
     showc
    -0.06
     getPlayer
    -0.06
    POSITIVE LOGITS
    /news
    0.07
    booking
    0.07
    seven
    0.06
     consultant
    0.06
    小姐
    0.06
    ORT
    0.06
    533
    0.06
     toplam
    0.06
     chron
    0.06
     masse
    0.06
    Act Density 0.041%

    No Known Activations