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

    Neuronpedia

    INDEX
    Explanations

    dialogue and narrative actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    !
    0.42
    ?
    0.37
    ...
    0.36
     implies
    0.36
    0.36
    0
    0.34
     imply
    0.33
    :
    0.32
     f
    0.32
    …
    0.31
    POSITIVE LOGITS
     вечером
    0.44
     လက်
    0.43
     Sitting
    0.43
     smiled
    0.42
     دونوں
    0.42
     sighed
    0.41
    Sitting
    0.41
    လက်
    0.41
     മണിക്ക
    0.41
     কিছুক্ষণ
    0.41
    Act Density 0.006%

    No Known Activations