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

    Neuronpedia

    INDEX
    Explanations

    Mr followed by punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     кухни
    0.44
    自带
    0.44
    新增
    0.40
     идеи
    0.40
    䉍
    0.39
    簌
    0.38
     острова
    0.38
     சப
    0.38
    <unused274>
    0.38
     línea
    0.38
    POSITIVE LOGITS
     Mr
    0.90
    Mr
    0.78
     Mister
    0.65
     mr
    0.64
     Mrs
    0.61
     MR
    0.57
    Mrs
    0.57
    mr
    0.54
     MRS
    0.54
     মিঃ
    0.52
    Act Density 0.009%

    No Known Activations