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

    Neuronpedia

    INDEX
    Explanations

    order, differencing, stationary

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    rieved
    0.25
    乱
    0.25
     Buckley
    0.25
     Distress
    0.25
     மிகப்பெ
    0.25
    大きな
    0.25
    kswagen
    0.24
     துன்ப
    0.24
     milliers
    0.24
    Worldwide
    0.24
    POSITIVE LOGITS
    kee
    0.23
    odon
    0.22
     smlou
    0.22
     ohm
    0.22
     zoom
    0.21
    у
    0.21
    皂
    0.21
    ك
    0.21
    хай
    0.21
    ᄋ
    0.20
    Act Density 0.001%

    No Known Activations