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

    Neuronpedia

    INDEX
    Explanations

    around the

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Pakistan
    0.45
    ைகோ
    0.44
     पाकिस्तान
    0.43
     Pakistan
    0.43
     پاکستانی
    0.39
     sacchar
    0.38
    BIB
    0.38
     Sachin
    0.38
     السعود
    0.38
    LEncoder
    0.38
    POSITIVE LOGITS
    指向
    0.41
     nearby
    0.39
    around
    0.39
    靠
    0.39
     окру
    0.39
    ser
    0.39
    abouts
    0.39
    ings
    0.38
    周辺
    0.38
     surrounded
    0.37
    Act Density 0.000%

    No Known Activations