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

    Neuronpedia

    INDEX
    Explanations

    Mary

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    volume
    0.70
     volume
    0.69
     volumen
    0.57
     finger
    0.57
     volumes
    0.56
     minimal
    0.56
     oh
    0.55
     SN
    0.54
     orang
    0.52
     session
    0.52
    POSITIVE LOGITS
    Mary
    0.86
    lavery
    0.84
    MARY
    0.84
     Austen
    0.83
    <unused1093>
    0.82
     Embroidery
    0.81
    篌
    0.81
     ചരി
    0.81
    <unused698>
    0.80
    <unused1883>
    0.80
    Act Density 0.001%

    No Known Activations