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

    Neuronpedia

    INDEX
    Explanations

    all rights reserved

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     all
    0.59
     все
    0.50
    قة
    0.46
     όλα
    0.44
     всі
    0.43
     всё
    0.41
     را
    0.41
     ALL
    0.40
     overalls
    0.40
     overlapping
    0.39
    POSITIVE LOGITS
    atet
    0.41
    सामान्य
    0.39
    。」
    0.39
    .|
    0.39
    ทั่ว
    0.38
    ."""
    0.38
    ."
    0.38
    worldwide
    0.38
     weltweit
    0.37
    nos
    0.37
    Act Density 0.000%

    No Known Activations