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

    Neuronpedia

    INDEX
    Explanations

    rare occasions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ה
    2.76
    𝐨
    2.74
    ीय
    2.58
    ්‍ර
    2.56
    𝐞
    2.49
    𝐝
    2.48
    erical
    2.48
    anjing
    2.45
    𝐲
    2.41
    ଼
    2.40
    POSITIVE LOGITS
    te
    2.54
     occasions
    2.30
    setwd
    2.29
    újo
    2.18
    ूहिक
    2.14
    me
    2.14
     Darüber
    2.12
    ly
    2.12
    cases
    2.11
     unes
    2.11
    Act Density 0.071%

    No Known Activations