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

    Neuronpedia

    INDEX
    Explanations

    as a, as requested

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     deverá
    0.27
     bør
    0.26
    nél
    0.26
     eller
    0.25
    Should
    0.25
    should
    0.24
    roweak
    0.24
     deberá
    0.23
     donnant
    0.23
     deberán
    0.23
    POSITIVE LOGITS
     a
    0.27
    作為
    0.26
     ως
    0.25
    作为
    0.25
     prerequisite
    0.24
     well
    0.23
     part
    0.23
     качестве
    0.23
     prelude
    0.23
     testament
    0.23
    Act Density 0.077%

    No Known Activations