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

    Neuronpedia

    INDEX
    Explanations

    repeating everything

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     нови
    0.48
     силы
    0.48
     deftly
    0.46
     iniziamo
    0.46
     beeindruck
    0.45
    礼物
    0.45
     ইতিহাসের
    0.45
    RatingDiff
    0.44
    িনবার্গ
    0.44
     underwhelming
    0.44
    POSITIVE LOGITS
    g
    0.44
     takže
    0.42
     u
    0.42
    f
    0.42
    q
    0.41
    h
    0.40
    fr
    0.39
    ad
    0.39
    uf
    0.38
    ev
    0.38
    Act Density 0.011%

    No Known Activations