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

    Neuronpedia

    INDEX
    Explanations

    adding

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     சமீ
    0.46
    oyama
    0.45
    əsi
    0.43
     AsRef
    0.42
     dobre
    0.41
     свет
    0.40
     utu
    0.39
    0.39
     высокой
    0.39
     طریقہ
    0.39
    POSITIVE LOGITS
     added
    1.14
     adding
    1.02
    添加
    1.02
     additions
    0.97
     添加
    0.97
    Adding
    0.96
     добавить
    0.95
     aggi
    0.95
    Added
    0.93
     добавля
    0.93
    Act Density 0.205%

    No Known Activations