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

    Neuronpedia

    INDEX
    Explanations

    news articles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     act
    -0.07
     Kickstarter
    -0.06
     Johannes
    -0.06
    conc
    -0.06
     米
    -0.06
     Comprehensive
    -0.06
    indre
    -0.06
    前に
    -0.06
    (viewModel
    -0.06
     fq
    -0.06
    POSITIVE LOGITS
    ------------------------------
    0.07
    ::|
    0.06
    _TRIGGER
    0.06
    /watch
    0.06
     اسلام
    0.06
    /*.
    0.06
    >xpath
    0.06
    ':{'
    0.06
     regards
    0.06
     استاد
    0.06
    Act Density 0.268%

    No Known Activations