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

    Neuronpedia

    INDEX
    Explanations

    ` and `task`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     आस्ट्रेलिया
    0.55
    টিয়া
    0.49
     ናቸው
    0.48
     প্রাধ
    0.46
     intravascular
    0.46
     இணைய
    0.45
     문제입니다
    0.45
     анали
    0.44
     पासवान
    0.43
    Extraction
    0.43
    POSITIVE LOGITS
    do
    0.56
     sekaligus
    0.54
    seh
    0.47
    div
    0.46
    db
    0.46
    ទៅ
    0.45
     d
    0.44
     divis
    0.44
    strtotime
    0.42
    .
    0.42
    Act Density 0.003%

    No Known Activations