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

    Neuronpedia

    INDEX
    Explanations

    shortlisting candidates or options

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    (
    0.71
     is
    0.69
    board
    0.64
    is
    0.63
    \
    0.62
    de
    0.61
    них
    0.58
    se
    0.58
    ↵
    0.57
    was
    0.56
    POSITIVE LOGITS
     finalists
    1.05
     finalist
    1.00
     shortlisted
    0.98
     shortlist
    0.76
    ра
    0.75
    которые
    0.75
    ي
    0.73
     contestants
    0.72
    İL
    0.72
    न्ग
    0.72
    Act Density 0.000%

    No Known Activations