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

    Neuronpedia

    INDEX
    Explanations

    Ned Flanders, Ned Stark

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Kil
    0.40
    న్న
    0.38
    חש
    0.38
    ilyl
    0.38
    ueuse
    0.37
    Kil
    0.36
    Mixin
    0.36
    pointee
    0.35
     التربيع
    0.35
    ప్ర
    0.34
    POSITIVE LOGITS
    Ned
    0.65
     Ned
    0.64
     NED
    0.62
    ned
    0.58
    NED
    0.58
     Neder
    0.50
    lands
    0.50
     Flanders
    0.47
     ned
    0.46
     nied
    0.45
    Act Density 0.002%

    No Known Activations