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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tus
    -0.07
    Ra
    -0.06
    포츠
    -0.06
    Tak
    -0.06
    iddleware
    -0.06
    _google
    -0.06
    boBox
    -0.06
    문제
    -0.06
     هفت
    -0.06
    (inp
    -0.06
    POSITIVE LOGITS
    كييف
    0.07
    Ether
    0.06
     freshness
    0.06
    +-
    0.06
    UL
    0.06
     promot
    0.06
     대상
    0.06
     obligation
    0.06
     willing
    0.06
     IDR
    0.06
    Act Density 0.065%

    No Known Activations