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

    Neuronpedia

    INDEX
    Explanations

    explaining complex topics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     በኋላ
    0.38
     ）
    0.37
     inférieure
    0.36
     спу
    0.34
     ispod
    0.34
    ）。
    0.34
     \%)$
    0.33
     дере
    0.33
     updateConfirm
    0.32
     dessous
    0.32
    POSITIVE LOGITS
     crucial
    0.50
     important
    0.48
     wonderful
    0.45
     fascinating
    0.45
    重要的
    0.45
     amazing
    0.44
    很容易
    0.43
    真的很
    0.42
    important
    0.42
     wonderfully
    0.42
    Act Density 0.055%

    No Known Activations