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

    Neuronpedia

    INDEX
    Explanations

    increment or before for major

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     asks
    0.51
     ⭐
    0.49
     disgr
    0.47
     death
    0.46
     компонентов
    0.46
     ceo
    0.46
     fazem
    0.45
     handover
    0.44
     divisive
    0.44
     components
    0.44
    POSITIVE LOGITS
    ون
    0.48
    排
    0.48
    지금
    0.47
    пи
    0.46
    बस
    0.45
    인
    0.45
    ड
    0.44
    푎
    0.44
    我
    0.43
    भारत
    0.43
    Act Density 0.000%

    No Known Activations