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

    Neuronpedia

    INDEX
    Explanations

    list items

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     매우
    0.44
     นอกจาก
    0.39
    </sup>
    0.39
     আমিও
    0.38
     তারাও
    0.38
     ceases
    0.37
    ↼
    0.37
     copied
    0.36
     outra
    0.36
     υπάρχει
    0.36
    POSITIVE LOGITS
    ഗത
    0.40
    dS
    0.39
    溆
    0.39
    बाट
    0.38
    timeInterval
    0.36
     astron
    0.35
    azolin
    0.35
    kD
    0.35
    ጠን
    0.35
    dN
    0.35
    Act Density 0.132%

    No Known Activations