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

    Neuronpedia

    INDEX
    Explanations

    different scripts and languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     แต่
    0.43
    졌
    0.43
    했고
    0.41
     alltid
    0.41
    Finish
    0.41
     vardı
    0.41
    íram
    0.40
     സ്ഥാന
    0.39
     restraint
    0.39
    但在
    0.39
    POSITIVE LOGITS
    aacute
    0.50
    電腦
    0.47
    ੳ
    0.44
    受信
    0.43
     collectibles
    0.43
     currencies
    0.43
    ितीय
    0.41
    ถือ
    0.41
     পারস্পরিক
    0.41
     пытается
    0.41
    Act Density 0.005%

    No Known Activations