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

    Neuronpedia

    INDEX
    Explanations

    large plastic containers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     jar
    0.77
     bowl
    0.75
    碗
    0.64
     saucepan
    0.63
    杯
    0.61
     Jar
    0.61
     cup
    0.60
    Bowl
    0.58
     plate
    0.57
     vial
    0.57
    POSITIVE LOGITS
     Rubber
    0.71
     tote
    0.65
    Rubber
    0.64
     Laundry
    0.63
     Tote
    0.61
     totes
    0.60
     laundry
    0.57
     tubs
    0.57
     Tub
    0.55
     tub
    0.55
    Act Density 0.017%

    No Known Activations