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

    Neuronpedia

    INDEX
    Explanations

    say "an"

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    anges
    0.35
    ange
    0.35
    说着
    0.34
    Ange
    0.33
    ANGE
    0.32
    ুনের
    0.30
    畈
    0.30
    OpenGL
    0.29
     CE
    0.29
    ўні
    0.29
    POSITIVE LOGITS
     an
    1.93
     aan
    1.76
     Aan
    1.01
    aan
    0.88
     به
    0.79
    an
    0.74
     ana
    0.70
     ان
    0.70
     ano
    0.69
     ан
    0.67
    Act Density 0.000%

    No Known Activations