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

    Neuronpedia

    INDEX
    Explanations

    request to do

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     soldados
    0.75
    Interpolator
    0.75
    nga
    0.75
    stitial
    0.75
    hny
    0.73
    rda
    0.72
    ampo
    0.71
    quez
    0.71
     obstáculos
    0.69
    álie
    0.68
    POSITIVE LOGITS
     مبنی
    1.61
     to
    1.25
    To
    1.05
    to
    1.02
     To
    0.98
     towards
    0.94
    ທີ່ຈະ
    0.93
    去做
    0.91
     visant
    0.88
     để
    0.87
    Act Density 0.219%

    No Known Activations