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

    Neuronpedia

    INDEX
    Explanations

    polite requests

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     alluvial
    0.42
     hadron
    0.40
     thatch
    0.39
     sulfide
    0.39
     fleece
    0.38
     flue
    0.38
     pulver
    0.37
     integrates
    0.37
     matrix
    0.36
     skapa
    0.36
    POSITIVE LOGITS
     Please
    0.67
    Please
    0.65
    please
    0.59
     Veuillez
    0.58
     कृपया
    0.57
     please
    0.57
    कृपया
    0.57
     пожалуйста
    0.55
    请
    0.52
     请
    0.50
    Act Density 4.274%

    No Known Activations