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

    Neuronpedia

    INDEX
    Explanations

    Ukrainian forces

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    nment
    0.38
    ogany
    0.38
    ீர
    0.37
    숍
    0.37
     состоя
    0.37
    شفى
    0.37
    ისი
    0.36
    ಿಣ
    0.36
     الطريقه
    0.35
    સ્તા
    0.35
    POSITIVE LOGITS
     teaching
    0.43
     OPT
    0.41
     bak
    0.40
    bak
    0.39
     predstav
    0.39
     Taw
    0.39
    หน่วย
    0.39
     COT
    0.38
     warto
    0.38
    ických
    0.38
    Act Density 0.000%

    No Known Activations