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

    Neuronpedia

    INDEX
    Explanations

    github

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     carbohydrate
    -0.07
    การเล
    -0.07
     Να
    -0.06
    自由
    -0.06
    Until
    -0.06
    [I
    -0.06
    ائج
    -0.06
    แนว
    -0.06
     그
    -0.06
    ضع
    -0.06
    POSITIVE LOGITS
     Argentine
    0.07
     giả
    0.07
    ithub
    0.06
    -work
    0.06
    cycles
    0.06
     abrupt
    0.06
     glEnable
    0.06
    /GPL
    0.06
    .Invoke
    0.06
     작업
    0.06
    Act Density 0.006%

    No Known Activations