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

    Neuronpedia

    INDEX
    Explanations

    Stop words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     soubor
    -0.08
    Downloader
    -0.06
    .dom
    -0.06
     Malaysia
    -0.06
     backers
    -0.06
    htm
    -0.06
     이러한
    -0.06
    &eacute
    -0.06
    .original
    -0.06
     Yep
    -0.06
    POSITIVE LOGITS
    plication
    0.07
    engers
    0.07
    ATRIX
    0.06
    PIO
    0.06
    ()],
    0.06
    opathic
    0.06
    اشین
    0.06
    _LS
    0.06
    UAL
    0.06
    AntiForgeryToken
    0.06
    Act Density 0.090%

    No Known Activations