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

    Neuronpedia

    INDEX
    Explanations

    DMCA takedown complaints

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Ge
    0.38
    uw
    0.38
    Ga
    0.37
    elah
    0.37
     Manor
    0.37
     Panama
    0.37
    ilibrium
    0.36
     Cooper
    0.36
     og
    0.35
    ̆
    0.35
    POSITIVE LOGITS
    ද්
    0.46
    Radiux
    0.45
     በሚ
    0.42
    喡
    0.41
     ಒಳ್ಳೆಯ
    0.41
     دي
    0.40
     تعدى
    0.40
    电子邮件
    0.39
    ствовали
    0.39
    भाषित
    0.39
    Act Density 0.000%

    No Known Activations