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

    Neuronpedia

    INDEX
    Explanations

    consulting firms and universities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    و
    0.72
    湋
    0.70
     громадян
    0.67
     калі
    0.65
    त्ता
    0.64
    وون
    0.63
     terá
    0.62
     aswell
    0.62
     católica
    0.61
    ل
    0.61
    POSITIVE LOGITS
     L
    0.70
    ﻳ
    0.69
    App
    0.66
     Intelig
    0.65
    <0x0D>
    0.64
    ใน
    0.64
     opiek
    0.63
     OZ
    0.63
    L
    0.62
     McKinsey
    0.60
    Act Density 0.011%

    No Known Activations