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

    Neuronpedia

    INDEX
    Explanations

    scaling frameworks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ista
    -0.08
     En
    -0.08
     назначения
    -0.08
     совершен
    -0.07
    ಳೆ
    -0.07
    tsi
    -0.07
    -En
    -0.07
    smith
    -0.07
     צ
    -0.07
     enclosure
    -0.07
    POSITIVE LOGITS
    .Keyword
    0.09
    ULONG
    0.09
    .slide
    0.08
     groceries
    0.08
    شاركة
    0.08
    .ad
    0.08
    сл
    0.08
    .share
    0.08
    gateway
    0.07
    .gov
    0.07
    Act Density 0.001%

    No Known Activations