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

    Neuronpedia

    INDEX
    Explanations

    it should

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ת
    1.27
    ↵↵
    1.23
    のです
    1.16
    なりません
    1.15
    СТИ
    1.15
    ין
    1.14
    сти
    1.11
    רק
    1.11
    ل
    1.11
    тину
    1.08
    POSITIVE LOGITS
    it
    2.03
     lleno
    1.52
    ik
    1.48
    가
    1.40
    ises
    1.34
    ită
    1.32
    ਆ
    1.31
    n
    1.27
     pelos
    1.26
    ५
    1.26
    Act Density 0.001%

    No Known Activations