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

    Neuronpedia

    INDEX
    Explanations

    clear contents

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     আলে
    0.39
    swick
    0.39
    Leaving
    0.38
    ليف
    0.38
    lsen
    0.37
     Magnolia
    0.37
    ادر
    0.35
     Heath
    0.35
    ropol
    0.35
     ceased
    0.35
    POSITIVE LOGITS
     Show
    0.54
     ▼
    0.49
    Show
    0.46
     show
    0.45
    show
    0.41
     Mostrar
    0.41
    Mostrar
    0.40
     Hide
    0.39
     hide
    0.39
     content
    0.38
    Act Density 0.000%

    No Known Activations