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

    Neuronpedia

    INDEX
    Explanations

    lying

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ak
    1.86
     Automobiles
    1.57
     réalisées
    1.55
    umum
    1.52
     omin
    1.50
     utilisées
    1.49
    DEPTH
    1.46
    दायक
    1.45
    queen
    1.45
     estando
    1.44
    POSITIVE LOGITS
    in
    2.09
    p
    1.87
    𝖾
    1.74
    อ
    1.73
    ી
    1.71
    아
    1.70
     Еще
    1.68
    о
    1.68
     belakang
    1.67
    ｉ
    1.66
    Act Density 0.003%

    No Known Activations