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

    Neuronpedia

    INDEX
    Explanations

    times

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    primir
    -0.07
    .Transactional
    -0.07
     researched
    -0.06
     питань
    -0.06
     aggregator
    -0.06
     공개
    -0.06
    imizin
    -0.06
    에게
    -0.06
    emode
    -0.06
     제출
    -0.06
    POSITIVE LOGITS
    (setting
    0.06
     dele
    0.06
     मल
    0.06
     tote
    0.06
     performer
    0.06
    _auto
    0.06
     Cp
    0.06
     ski
    0.06
     tua
    0.06
     poder
    0.06
    Act Density 0.014%

    No Known Activations