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

    Neuronpedia

    INDEX
    Explanations

    code and programming constructs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Otras
    -0.91
    enums
    -0.81
    菴
    -0.80
    ⡷
    -0.79
    ztés
    -0.78
    sä
    -0.77
    Länge
    -0.77
     Kalender
    -0.77
    Aggregation
    -0.75
    ссия
    -0.75
    POSITIVE LOGITS
    inete
    0.88
     Crea
    0.84
     layout
    0.84
    create
    0.82
    ress
    0.82
     Creates
    0.81
     createState
    0.80
    nstein
    0.80
    hancing
    0.79
    真剣
    0.76
    Act Density 0.001%

    No Known Activations