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

    Neuronpedia

    INDEX
    Explanations

    smiling and grinning

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    旄
    0.40
     discussion
    0.40
    rocessor
    0.39
    績
    0.37
     complains
    0.37
     condense
    0.37
     discuter
    0.37
     overse
    0.35
     статей
    0.35
     ادب
    0.35
    POSITIVE LOGITS
     grin
    0.92
     smile
    0.81
     beaming
    0.81
     crooked
    0.80
     grinned
    0.77
     wry
    0.75
     širo
    0.74
     genuine
    0.74
     улы
    0.73
     sonrisa
    0.71
    Act Density 0.033%

    No Known Activations