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

    Neuronpedia

    INDEX
    Explanations

    need to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Với
    0.99
    Với
    0.99
     شدن
    0.95
     Bây
    0.95
     כאשר
    0.95
     siendo
    0.95
    ሑ
    0.94
     ندارد
    0.92
    𝖾
    0.92
     несмотря
    0.92
    POSITIVE LOGITS
     to
    2.43
     να
    1.61
    to
    1.38
     să
    1.26
    ToAdd
    1.15
    ToBe
    1.12
    ที่จะ
    1.06
     để
    1.00
    ທີ່ຈະ
    0.99
     לה
    0.99
    Act Density 0.185%

    No Known Activations