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

    Neuronpedia

    INDEX
    Explanations

    alignment and order

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     feedwater
    0.43
    olved
    0.40
    بل
    0.40
    的操作
    0.40
    豆
    0.40
     has
    0.40
     telo
    0.39
    لاح
    0.39
    ्ल
    0.38
     inoculum
    0.38
    POSITIVE LOGITS
     Свет
    0.52
    ÇA
    0.50
     свет
    0.48
    defs
    0.47
    Ratings
    0.47
    ähne
    0.46
    賺
    0.46
     eBooks
    0.46
    SYMBOL
    0.46
     Satisfaction
    0.46
    Act Density 0.001%

    No Known Activations