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

    Neuronpedia

    INDEX
    Explanations

    Chick-fil-A

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Couldn
    0.44
    menos
    0.43
     Harrison
    0.43
     আর্থ
    0.40
     Claims
    0.40
    arno
    0.40
    roben
    0.40
    opez
    0.40
    koch
    0.39
    يع
    0.39
    POSITIVE LOGITS
    zetac
    0.41
     gunpowder
    0.40
     scones
    0.40
     disintegrated
    0.40
     muffins
    0.39
    ว์
    0.39
     platinum
    0.37
     conductive
    0.37
     breather
    0.37
     brakes
    0.37
    Act Density 0.001%

    No Known Activations