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

    Neuronpedia

    INDEX
    Explanations

    may can followed by verb

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Якщо
    0.42
    вніш
    0.40
    FAF
    0.39
     Фа
    0.38
    젹
    0.38
    Faction
    0.38
     জাফর
    0.38
     Пан
    0.38
    Fa
    0.38
     архівів
    0.37
    POSITIVE LOGITS
     be
    0.58
     de
    0.48
    )\
    0.45
    de
    0.41
    }\
    0.40
    )
    0.38
     have
    0.38
     del
    0.38
     seper
    0.36
    e
    0.36
    Act Density 0.001%

    No Known Activations