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

    Neuronpedia

    INDEX
    Explanations

    database column definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     a
    0.70
     Belize
    0.63
    在
    0.63
     UAE
    0.61
    。
    0.60
     Sainsbury
    0.59
     Ladakh
    0.59
     Brunei
    0.59
     Boats
    0.58
     Pakistan
    0.58
    POSITIVE LOGITS
    ే
    0.83
    н
    0.82
    ik
    0.75
    "}
    0.74
    т
    0.74
    л
    0.71
    ற்ற
    0.69
    ر
    0.68
     eagerness
    0.68
    iz
    0.66
    Act Density 0.001%

    No Known Activations