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

    Neuronpedia

    INDEX
    Explanations

    single or individual units

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ğraf
    0.73
     Asoci
    0.72
     ভাঁ
    0.72
     Ali
    0.70
     ಕೈ
    0.70
     Weiss
    0.70
     ভাগ
    0.67
     όπου
    0.67
     Hyp
    0.67
     wraps
    0.66
    POSITIVE LOGITS
     seeding
    0.65
    negl
    0.63
    一人
    0.62
     probablemente
    0.61
    ufu
    0.60
    дев
    0.59
    ひとり
    0.58
    singleton
    0.57
    单个
    0.57
    一个人
    0.57
    Act Density 0.052%

    No Known Activations