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

    Neuronpedia

    INDEX
    Explanations

    version and port numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     version
    0.74
     phiên
    0.58
     версия
    0.55
     versions
    0.55
     версию
    0.54
     Version
    0.54
     versi
    0.50
     versione
    0.48
     lasted
    0.48
    こだわり
    0.48
    POSITIVE LOGITS
    ing
    0.47
    age
    0.45
    ט
    0.43
     Сим
    0.40
    쮿
    0.40
    bef
    0.40
     ROUILLER
    0.40
    젹
    0.40
     здійс
    0.39
    迲
    0.39
    Act Density 0.037%

    No Known Activations