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

    Neuronpedia

    INDEX
    Explanations

    specifications and measurements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     in
    0.47
    ↵
    0.46
    ↵↵
    0.43
     Package
    0.43
     control
    0.42
     segments
    0.42
     adoption
    0.42
     type
    0.42
     segment
    0.41
     SDL
    0.41
    POSITIVE LOGITS
    udarstven
    0.50
    UIAlert
    0.48
    哫
    0.48
    𝚐
    0.47
    itatif
    0.46
    न्यू
    0.46
    จัย
    0.45
     betterment
    0.45
    捙
    0.45
    ваем
    0.45
    Act Density 0.003%

    No Known Activations