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

    Neuronpedia

    INDEX
    Explanations

    numbers and characters like 'x'

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Room
    0.80
     rooms
    0.75
    room
    0.74
     room
    0.74
    oom
    0.74
    Room
    0.73
    ns
    0.72
     Rooms
    0.71
    nth
    0.71
    ্বক
    0.70
    POSITIVE LOGITS
    <0x95>
    0.91
    三
    0.76
     六
    0.75
     ৩
    0.74
    六
    0.73
     percolation
    0.73
     seis
    0.72
     activeButton
    0.70
     hyperplasia
    0.70
     다섯
    0.70
    Act Density 0.001%

    No Known Activations