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

    Neuronpedia

    INDEX
    Explanations

    names of people and mythological figures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     زیرمه
    0.96
    t
    0.91
     fertil
    0.89
     وړیا
    0.83
     سایټ
    0.81
     ආරක්ෂ
    0.79
     ස්ථා
    0.79
     ګرځنده
    0.77
     appliquée
    0.75
     зміню
    0.75
    POSITIVE LOGITS
    4
    1.27
    :
    1.26
    5
    1.25
    ،
    1.16
    、
    1.10
    (
    1.05
    6
    1.05
    3
    1.01
    ，
    1.00
    с
    0.96
    Act Density 0.020%

    No Known Activations