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

    Neuronpedia

    INDEX
    Explanations

    Stef

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Window
    -0.06
     이루
    -0.06
     feet
    -0.06
     увид
    -0.06
     )),↵
    -0.05
     sugar
    -0.05
    Polit
    -0.05
     Portland
    -0.05
    領
    -0.05
    ____
    -0.05
    POSITIVE LOGITS
     postings
    0.06
    ững
    0.06
    유머
    0.06
    ibBundleOrNil
    0.06
     Lawyer
    0.06
    าษฎร
    0.06
    ussen
    0.06
     nitel
    0.06
    ointments
    0.06
    hhh
    0.06
    Act Density 0.138%

    No Known Activations