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

    Neuronpedia

    INDEX
    Explanations

    programming constructs and imports

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    5
    0.28
    9
    0.24
     hung
    0.23
    6
    0.23
    8
    0.22
    anesulfonyl
    0.22
     Chile
    0.22
     skul
    0.22
    FirstOrDefault
    0.22
    7
    0.22
    POSITIVE LOGITS
     время
    0.24
     уте
    0.24
    ።
    0.24
     razvoj
    0.22
     പരാ
    0.22
     सोड
    0.22
    ்
    0.22
     упро
    0.22
     во
    0.21
     формирование
    0.21
    Act Density 0.068%

    No Known Activations