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

    Neuronpedia

    INDEX
    Explanations

    collar

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    اب
    0.37
     ه
    0.37
    AHN
    0.36
     βρί
    0.35
     सईद
    0.35
     Тогда
    0.34
    ሳት
    0.34
    나
    0.34
     హ
    0.34
     സു
    0.33
    POSITIVE LOGITS
     neckline
    0.34
     collar
    0.34
     company
    0.30
     shirt
    0.30
     quantifiable
    0.30
    も含
    0.30
     production
    0.30
     cowling
    0.30
    ubh
    0.29
     cleverly
    0.29
    Act Density 0.001%

    No Known Activations