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

    Neuronpedia

    INDEX
    Explanations

    GitHub discussions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _news
    -0.07
    .Action
    -0.07
     Barton
    -0.07
     او
    -0.06
    .gradle
    -0.06
    _CREATED
    -0.06
     freaking
    -0.06
     sustainability
    -0.06
    .Method
    -0.06
     hug
    -0.06
    POSITIVE LOGITS
    rect
    0.07
    kses
    0.07
    replacement
    0.07
    baş
    0.07
     obtener
    0.06
     linen
    0.06
     Ratings
    0.06
    {{$
    0.06
    countries
    0.06
    ınızı
    0.06
    Act Density 0.063%

    No Known Activations