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

    Neuronpedia

    INDEX
    Explanations

    articles and possessives before nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    𝔻
    0.76
    לי
    0.72
    用品
    0.67
    𝕕
    0.66
    ילות
    0.66
    ংকর
    0.63
    謐
    0.63
    ively
    0.63
    𝕌
    0.63
    ליו
    0.63
    POSITIVE LOGITS
     cabbage
    1.01
     brakes
    1.00
     ambulances
    0.93
     ambulance
    0.91
     ferry
    0.91
     tomatoes
    0.91
     haters
    0.89
     bulldozer
    0.89
     taxi
    0.88
     geese
    0.87
    Act Density 0.240%

    No Known Activations