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
    coat
    -0.08
     asker
    -0.08
     negotiate
    -0.08
     நல்ல
    -0.07
     நிற
    -0.07
     שאין
    -0.07
    ાના
    -0.07
     எண்ண
    -0.07
     economía
    -0.07
    arum
    -0.07
    POSITIVE LOGITS
     Watt
    0.08
    ️⃣
    0.08
     ví
    0.08
     Mountains
    0.07
    �
    0.07
     hectares
    0.07
    �
    0.07
     fatalities
    0.07
     cabins
    0.07
     lakh
    0.07
    Act Density 0.321%

    No Known Activations