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

    Neuronpedia

    INDEX
    Explanations

    peer-to-peer networks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     entender
    0.41
    ➣
    0.40
     доходов
    0.40
     ingrédients
    0.39
    <0xCF>
    0.39
     constitué
    0.38
     carried
    0.38
     applauded
    0.38
     pranzo
    0.38
     imbued
    0.38
    POSITIVE LOGITS
    ный
    0.43
    й
    0.37
    S
    0.34
    اس
    0.33
    Styl
    0.32
    ли
    0.31
    ors
    0.31
    وا
    0.30
    وي
    0.30
    ји
    0.30
    Act Density 0.003%

    No Known Activations