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

    Neuronpedia

    INDEX
    Explanations

    you can control

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    cannot
    0.45
    робнее
    0.43
     pernyataan
    0.40
    Saving
    0.39
     നമഃ
    0.39
    today
    0.38
    غانستان
    0.38
     исправ
    0.38
    敘
    0.38
    वला
    0.38
    POSITIVE LOGITS
     citrus
    0.45
     çeşitli
    0.45
     tribes
    0.45
     fueling
    0.44
    𝚒
    0.42
     বেশ
    0.40
     ethn
    0.40
     wildflowers
    0.40
     топли
    0.40
     prepping
    0.40
    Act Density 0.001%

    No Known Activations