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

    Neuronpedia

    INDEX
    Explanations

    conclusion or next step

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    off
    0.49
    paint
    0.47
    search
    0.47
    odge
    0.47
    black
    0.46
    maintain
    0.46
    use
    0.45
    augh
    0.45
    erek
    0.45
    awk
    0.45
    POSITIVE LOGITS
     cranberries
    0.55
     résultats
    0.54
     pickles
    0.53
     Dét
    0.52
     lyrics
    0.51
     diets
    0.51
     à
    0.50
     spices
    0.50
     sweets
    0.50
     attendance
    0.49
    Act Density 0.014%

    No Known Activations