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

    Neuronpedia

    INDEX
    Explanations

    academic abstracts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .get
    -0.06
    лек
    -0.06
     Craw
    -0.06
    ahy
    -0.06
    ymous
    -0.06
     PhpStorm
    -0.06
     blessed
    -0.06
    _air
    -0.05
     cached
    -0.05
     JFK
    -0.05
    POSITIVE LOGITS
    .providers
    0.07
    ometry
    0.07
     식
    0.07
     vite
    0.07
    .SqlClient
    0.07
    xygen
    0.06
     Solic
    0.06
    phrase
    0.06
     fighters
    0.06
     Bret
    0.06
    Act Density 0.047%

    No Known Activations