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

    Neuronpedia

    INDEX
    Explanations

    door, cash, services, time

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     دي
    0.52
     ponctu
    0.49
     כמו
    0.47
     sob
    0.47
     الذين
    0.46
     mutat
    0.46
    Bey
    0.46
     escult
    0.46
     آور
    0.46
     עם
    0.46
    POSITIVE LOGITS
    द
    0.49
    ह
    0.44
    .),
    0.43
    stl
    0.43
    ools
    0.42
    цена
    0.42
     स
    0.41
     regulations
    0.41
    .',
    0.41
    scored
    0.41
    Act Density 0.000%

    No Known Activations