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

    Neuronpedia

    INDEX
    Explanations

    a

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Warwick
    0.33
     Ле
    0.31
     Regent
    0.29
     Diabetic
    0.29
     Presidente
    0.29
     President
    0.29
     Leon
    0.28
     이렇게
    0.28
    注意到
    0.28
     Broughton
    0.28
    POSITIVE LOGITS
     outras
    0.33
    otras
    0.32
    隠
    0.32
     lois
    0.30
    клады
    0.30
     других
    0.30
    itares
    0.30
     consequatur
    0.30
    퍄
    0.30
     otras
    0.29
    Act Density 0.014%

    No Known Activations