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

    Neuronpedia

    INDEX
    Explanations

    light and light-related phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    0.47
    0.43
    0.41
    lesson
    0.39
    的看着
    0.39
    0.39
    0.38
     лекар
    0.38
    প্লে
    0.38
    atypes
    0.37
    POSITIVE LOGITS
    bulb
    0.88
     bulb
    0.78
     light
    0.77
    enment
    0.70
     bulbs
    0.70
    ened
    0.68
     Bulb
    0.68
     terang
    0.67
     Light
    0.66
    hearted
    0.66
    Act Density 0.052%

    No Known Activations