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

    Neuronpedia

    INDEX
    Explanations

    live chat, demo, traffic, activities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    dev
    0.43
    ণ
    0.42
    log
    0.42
    logical
    0.41
    j
    0.40
    matrix
    0.39
    l
    0.38
    assumption
    0.38
    short
    0.38
    lateral
    0.37
    POSITIVE LOGITS
     live
    0.90
    LIVE
    0.80
    Live
    0.79
     Live
    0.78
     LIVE
    0.78
    ライブ
    0.76
     लाइव
    0.71
    live
    0.65
    直播
    0.64
     canlı
    0.63
    Act Density 0.009%

    No Known Activations