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

    Neuronpedia

    INDEX
    Explanations

    Le Guin, Universalization, full view

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     González
    0.83
     Ked
    0.79
    Allison
    0.78
     श्रीराम
    0.77
     Kenn
    0.76
    Ked
    0.76
     للصف
    0.75
     Stacy
    0.75
     للص
    0.75
     لص
    0.75
    POSITIVE LOGITS
     u
    1.43
     ইউ
    1.42
     U
    1.40
    ยู
    1.38
    U
    1.35
     UA
    1.34
    DU
    1.30
    PU
    1.30
     யூ
    1.28
    ইউ
    1.28
    Act Density 1.785%

    No Known Activations