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

    Neuronpedia

    INDEX
    Explanations

    family and parents

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Бу
    0.22
     Virology
    0.21
    ያንዳ
    0.21
    ጀት
    0.21
    벨
    0.21
    न्स
    0.21
    ローズ
    0.21
    뢰
    0.21
    냅
    0.21
     cessation
    0.20
    POSITIVE LOGITS
    ed
    0.45
    er
    0.33
    ার
    0.29
    א
    0.29
    id
    0.28
    ,
    0.28
    é
    0.28
    ون
    0.27
    es
    0.26
    ే
    0.26
    Act Density 0.111%

    No Known Activations