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

    Neuronpedia

    INDEX
    Explanations

    states and measurements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Character
    0.54
     캐릭터
    0.52
    Bek
    0.52
    Anna
    0.50
    Drain
    0.49
    Từ
    0.49
    Antes
    0.48
    Câu
    0.48
    Begriff
    0.47
    Nella
    0.47
    POSITIVE LOGITS
     at
    0.49
     MA
    0.48
     Duh
    0.45
     SA
    0.45
    بوط
    0.44
     cov
    0.43
     loi
    0.43
     adjusts
    0.43
     hu
    0.43
     halfway
    0.43
    Act Density 0.006%

    No Known Activations