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

    Neuronpedia

    INDEX
    Explanations

    fill in the blanks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     produz
    0.44
     సూ
    0.42
     اسماء
    0.42
     للان
    0.42
    Durante
    0.41
    риста
    0.41
    Después
    0.41
    жает
    0.41
     bekom
    0.40
     volonté
    0.40
    POSITIVE LOGITS
     स्टाफ
    0.51
    requested
    0.45
     Nr
    0.45
     servicing
    0.44
    यर
    0.43
     Contour
    0.42
    랑
    0.42
    ਤ
    0.41
    ropshire
    0.41
    তামূলক
    0.41
    Act Density 0.003%

    No Known Activations