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

    Neuronpedia

    INDEX
    Explanations

    food and places

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    आई
    0.77
    يديا
    0.76
    喔
    0.76
    (${
    0.75
    Radio
    0.74
    哦
    0.73
    ջ
    0.72
     telev
    0.71
    털
    0.71
    ຈ
    0.70
    POSITIVE LOGITS
     eateries
    0.80
     denaturation
    0.77
    feit
    0.77
     tours
    0.76
    ungere
    0.73
     calls
    0.73
     meats
    0.72
     restaurants
    0.72
     Biot
    0.71
     workpiece
    0.71
    Act Density 0.000%

    No Known Activations