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

    Neuronpedia

    INDEX
    Explanations

    Matt Reeves' Grace

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    stderr
    0.38
     fucking
    0.37
     noastră
    0.35
     Chúng
    0.34
     nossa
    0.33
     opposes
    0.33
     freaking
    0.33
     blames
    0.33
    思考
    0.32
     наших
    0.32
    POSITIVE LOGITS
    اؤن
    0.36
     പ്രദേശ
    0.36
    عمل
    0.35
    绚
    0.35
    ార
    0.34
     판매
    0.34
    .??.??"]
    0.34
     완
    0.34
     fiberglass
    0.34
     Raceway
    0.34
    Act Density 0.007%

    No Known Activations