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

    Neuronpedia

    INDEX
    Explanations

    wind turbines

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    с
    0.78
    I
    0.69
     I
    0.68
     OAuth
    0.66
     swagger
    0.64
     stronghold
    0.64
    มาตรฐาน
    0.61
     SQL
    0.57
    м
    0.57
     Urology
    0.56
    POSITIVE LOGITS
     incentiv
    0.75
    ၎င်း
    0.59
     on
    0.58
    中国
    0.57
     dansk
    0.57
     jeopard
    0.56
    Escolhido
    0.55
    pj
    0.55
     Antennes
    0.54
    ުޅ
    0.54
    Act Density 0.010%

    No Known Activations