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

    Neuronpedia

    INDEX
    Explanations

    please and requests

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     mismatched
    0.40
     inappropriately
    0.40
     differing
    0.37
    왤
    0.37
     whether
    0.36
     assent
    0.36
     supplemental
    0.35
     banding
    0.35
     linkages
    0.35
     annoyance
    0.35
    POSITIVE LOGITS
     Kindly
    0.61
     Voici
    0.57
    Voici
    0.53
     Please
    0.52
    Kindly
    0.47
     ขอ
    0.47
    ´
    0.47
     пожалуйста
    0.47
     부탁
    0.46
    жалуйста
    0.46
    Act Density 0.026%

    No Known Activations