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

    Neuronpedia

    INDEX
    Explanations

    carbon footprint and rash

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     wretched
    0.54
     Ελλάδα
    0.53
     heartache
    0.50
     mayam
    0.50
     çözüm
    0.49
     гля
    0.48
    ˧
    0.47
     heartbreaking
    0.47
     ไทย
    0.47
     ديسمبر
    0.46
    POSITIVE LOGITS
    。
    0.56
     I
    0.51
    shaped
    0.49
    取り
    0.48
    types
    0.48
    良好
    0.48
    tain
    0.48
     abilities
    0.47
    task
    0.47
    options
    0.46
    Act Density 0.001%

    No Known Activations