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

    Neuronpedia

    INDEX
    Explanations

    developed by companies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Для
    0.63
     identified
    0.62
     判断
    0.60
     но
    0.59
     χωρίς
    0.58
     ==
    0.58
     admitted
    0.58
     Notas
    0.57
     notas
    0.57
     மாதம்
    0.57
    POSITIVE LOGITS
    MktCap
    0.72
    Flavor
    0.67
    Tommy
    0.66
    Elon
    0.63
    <unused311>
    0.63
    Josh
    0.63
    ൻ
    0.61
     vendeurs
    0.61
    Noah
    0.60
    Bloomberg
    0.60
    Act Density 0.004%

    No Known Activations