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

    Neuronpedia

    INDEX
    Explanations

    ма followed by words about size/quantity/possession

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ui
    0.41
    ul
    0.40
     ma
    0.39
    ang
    0.39
    uls
    0.39
    allist
    0.38
    üy
    0.38
    Сере
    0.38
     mash
    0.37
    vex
    0.37
    POSITIVE LOGITS
    щей
    0.42
    )!=
    0.39
    λον
    0.38
    entemente
    0.38
    穼
    0.37
    стон
    0.37
    䨐
    0.37
    номет
    0.37
    сив
    0.36
     Nicholson
    0.36
    Act Density 0.001%

    No Known Activations