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

    Neuronpedia

    INDEX
    Explanations

    emphatic 'I' statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    😊
    0.41
    rising
    0.40
    大切
    0.40
    ของเรา
    0.39
     :)
    0.39
    newItem
    0.38
    นิยม
    0.38
     rising
    0.38
     exciting
    0.38
    Rising
    0.38
    POSITIVE LOGITS
     emphatically
    0.66
     repeat
    0.61
     emphasize
    0.58
     reiterate
    0.57
     seriously
    0.57
     warned
    0.55
     emphasise
    0.54
    Seriously
    0.54
    repeat
    0.53
     Seriously
    0.53
    Act Density 0.047%

    No Known Activations