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

    Neuronpedia

    INDEX
    Explanations

    gaming and concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    water
    0.48
    sample
    0.48
    miss
    0.45
    linked
    0.45
    on
    0.45
    detached
    0.44
     buckets
    0.43
    total
    0.43
    sleep
    0.43
    un
    0.42
    POSITIVE LOGITS
     তৈ
    0.51
     بسیار
    0.50
     Nên
    0.48
     Featuring
    0.46
     Vlog
    0.44
    ‼️
    0.44
     Поэтому
    0.43
     oyunc
    0.43
    🫶
    0.43
    ICENSE
    0.43
    Act Density 0.001%

    No Known Activations