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

    Neuronpedia

    INDEX
    Explanations

    everyone knows

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ли
    0.96
    栩
    0.96
    bidden
    0.96
    geojson
    0.95
    ０
    0.95
    withtag
    0.95
    ות
    0.93
    rufen
    0.92
     knn
    0.91
    yecto
    0.90
    POSITIVE LOGITS
     Babies
    0.88
     Taxes
    0.86
     jerseys
    0.85
     ruthenium
    0.84
     variedades
    0.83
    ्
    0.81
    ดิ
    0.80
    ↵↵
    0.80
     taxes
    0.80
    జ
    0.80
    Act Density 0.000%

    No Known Activations