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

    Neuronpedia

    INDEX
    Explanations

    numbers before identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ورٹی
    0.50
    DesIP
    0.49
    𒊒
    0.48
    鹖
    0.47
    謖
    0.47
    >)`](
    0.46
     códigos
    0.46
    desIP
    0.46
    လိုအပ်
    0.46
     पाठ्यक्रमों
    0.46
    POSITIVE LOGITS
     No
    0.66
     №
    0.65
    0.58
    №
    0.56
    No
    0.55
    /
    0.54
     number
    0.53
     Nr
    0.49
     Number
    0.48
     নং
    0.48
    Act Density 0.003%

    No Known Activations