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

    Neuronpedia

    INDEX
    Explanations

    plastic bins

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    情感
    0.76
     бота
    0.75
     पाठ
    0.72
    तिहास
    0.72
    relu
    0.71
     தெரிந்த
    0.70
    ஔ
    0.70
     அழி
    0.70
    种子
    0.70
    appid
    0.69
    POSITIVE LOGITS
     shelves
    1.85
     shelving
    1.77
     adjustable
    1.72
     Adjustable
    1.62
     desks
    1.61
     drawers
    1.58
     racks
    1.57
     shelf
    1.53
     bookcases
    1.49
     cabinets
    1.48
    Act Density 0.318%

    No Known Activations