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

    Neuronpedia

    INDEX
    Explanations

    a new neighbor

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     satir
    0.45
     mision
    0.44
    NotDefined
    0.43
    ISION
    0.42
    ਿਆ
    0.42
     errone
    0.42
     resemble
    0.41
    THANK
    0.41
     dabb
    0.41
     Arac
    0.41
    POSITIVE LOGITS
     another
    0.41
     फा
    0.40
     bows
    0.40
    میان
    0.39
     Đ
    0.38
     روان
    0.38
     سي
    0.38
     fellow
    0.38
     P
    0.38
     зі
    0.37
    Act Density 0.000%

    No Known Activations