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

    Neuronpedia

    INDEX
    Explanations

    automated code review

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    dade
    0.51
     ర
    0.45
    rů
    0.45
    իտ
    0.45
    ាំង
    0.44
    handlung
    0.44
    dor
    0.44
     gebruik
    0.44
     రు
    0.43
     electroly
    0.43
    POSITIVE LOGITS
    พิมพ์
    0.44
    UT
    0.42
    ภาษา
    0.42
    January
    0.41
     PDF
    0.40
     myopia
    0.40
    OWA
    0.40
    с
    0.40
    ındaki
    0.39
    URLs
    0.39
    Act Density 0.029%

    No Known Activations