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

    Neuronpedia

    INDEX
    Explanations

    SQL SELECT statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ４
    0.61
    ６
    0.54
    prevent
    0.52
    ﻼ
    0.50
    တို့ကို
    0.50
     వీరి
    0.50
    cdot
    0.49
    ۶
    0.49
     fruitful
    0.48
    ίες
    0.48
    POSITIVE LOGITS
    מ
    0.64
    ת
    0.62
     appartamento
    0.62
    تو
    0.57
     bungalows
    0.57
     />);
    0.55
     condos
    0.54
     on
    0.53
     intereses
    0.52
     Natl
    0.52
    Act Density 0.008%

    No Known Activations