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

    Neuronpedia

    INDEX
    Explanations

    Scottish places and regions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ٹیک
    0.41
     اندراج
    0.41
    ႉ
    0.39
    蛇
    0.38
     desempeño
    0.38
    招生
    0.38
    醉
    0.38
     Tatha
    0.37
    衚
    0.37
    ભા
    0.37
    POSITIVE LOGITS
     Dum
    1.13
    Dum
    1.06
     Galloway
    0.90
     dum
    0.83
    dum
    0.77
     Locker
    0.76
     DG
    0.65
     locker
    0.64
     Kirkpatrick
    0.61
     dumplings
    0.60
    Act Density 0.001%

    No Known Activations