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

    Neuronpedia

    INDEX
    Explanations

    parsing code or text segments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Green
    0.41
    Check
    0.40
    Zip
    0.40
     ব্যবসার
    0.40
    aspid
    0.39
    APPLE
    0.39
    Kiss
    0.38
    Í
    0.38
     управления
    0.38
     проверить
    0.38
    POSITIVE LOGITS
    就开始
    0.46
    ！！！
    0.42
     fooling
    0.41
     begun
    0.40
     başladı
    0.40
     inital
    0.40
    મુ
    0.40
     inizi
    0.40
     آغاز
    0.39
     dito
    0.39
    Act Density 0.005%

    No Known Activations