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

    Neuronpedia

    INDEX
    Explanations

    date and culture formatting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     করিয়
    0.39
    गोलिक
    0.38
    brides
    0.38
     चरम
    0.38
     Scud
    0.38
    utant
    0.37
    僑
    0.37
    ফিকুল
    0.36
     அடிகள்
    0.36
    ()}\
    0.36
    POSITIVE LOGITS
     साई
    0.45
     villa
    0.44
     बांग
    0.43
     pü
    0.42
     каз
    0.40
     パン
    0.40
     jumped
    0.39
    小麦
    0.38
    Villa
    0.38
     Gluten
    0.38
    Act Density 0.000%

    No Known Activations