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

    Neuronpedia

    INDEX
    Explanations

    lists, numbers, non-English characters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    🤭
    0.48
    🤪
    0.42
     lenght
    0.41
    𝙰
    0.41
    rasi
    0.41
     रोमांटिक
    0.41
    🥰
    0.41
    sizes
    0.40
    🧭
    0.40
     approval
    0.39
    POSITIVE LOGITS
     βαθ
    0.41
    实体
    0.38
     υψη
    0.37
    నా
    0.36
    बाट
    0.34
     अहं
    0.34
     ২০১৪
    0.34
     ಬ್ಯಾ
    0.33
     সাড়ে
    0.32
     облада
    0.32
    Act Density 0.001%

    No Known Activations