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

    Neuronpedia

    INDEX
    Explanations

    list formatting, thematic sections

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    साथ
    0.26
    StarGo
    0.26
     with
    0.25
    그러나
    0.25
     плюс
    0.24
     другими
    0.24
     लेकिन
    0.24
    とともに
    0.24
     compared
    0.24
     వివర
    0.24
    POSITIVE LOGITS
     Firstly
    0.30
     przede
    0.29
     ①
    0.28
     ✅
    0.27
    :
    0.27
    0.27
    ①
    0.27
     ✓
    0.25
     Viele
    0.24
     boş
    0.24
    Act Density 0.153%

    No Known Activations