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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     selectively
    -0.07
     flawless
    -0.07
     sounding
    -0.06
    "How
    -0.06
     qr
    -0.06
     устра
    -0.06
     negative
    -0.06
     pyt
    -0.06
     lehet
    -0.06
     repreh
    -0.06
    POSITIVE LOGITS
     Zimbabwe
    0.07
    .cast
    0.07
     Cardinals
    0.06
    .')↵
    0.06
     محصولات
    0.06
    653
    0.06
     دام
    0.06
     chromium
    0.06
     lar
    0.06
     META
    0.06
    Act Density 0.002%

    No Known Activations