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

    Neuronpedia

    INDEX
    Explanations

    else, but, lakini

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     under
    0.73
     다양한
    0.70
     sociaux
    0.70
     imposes
    0.70
     constamment
    0.68
     Under
    0.67
     socially
    0.66
     سلسلة
    0.66
     제한
    0.66
    Menurut
    0.66
    POSITIVE LOGITS
    但
    1.10
    但在
    1.10
     lakini
    1.07
     but
    1.07
    কিন্তু
    1.05
     लेकिन
    1.04
     ولكن
    1.03
    लेकिन
    1.01
     但
    1.01
    else
    1.01
    Act Density 0.335%

    No Known Activations