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

    Neuronpedia

    INDEX
    Explanations

    every followed by time or quantity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    それぞれの
    1.01
    人员
    0.99
    の一つ
    0.93
    er
    0.86
    ्री
    0.85
    is
    0.85
     각각
    0.85
     কাজটি
    0.85
     واحدة
    0.84
     společnosti
    0.83
    POSITIVE LOGITS
     few
    1.35
     fois
    1.23
    few
    1.11
    ewhere
    1.05
    گز
    1.05
    िश्च
    1.01
     pocos
    1.01
     så
    1.00
     hagan
    0.99
    ඳු
    0.99
    Act Density 0.007%

    No Known Activations