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

    Neuronpedia

    INDEX
    Explanations

    related to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    လည်း
    0.22
    ’।
    0.21
     nejen
    0.21
     teljesen
    0.21
     atthe
    0.21
     באתר
    0.21
     বিনামূল্যে
    0.20
     þat
    0.20
    ◾
    0.20
    യാണ്
    0.20
    POSITIVE LOGITS
    related
    0.44
     related
    0.40
     관련
    0.33
    相关的
    0.31
     தொடர்பான
    0.31
    focused
    0.31
    相關
    0.31
    centric
    0.30
     RELATED
    0.30
    Related
    0.29
    Act Density 1.308%

    No Known Activations