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

    Neuronpedia

    INDEX
    Explanations

    real-world application or deployment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    笑了
    0.40
     Karn
    0.38
    ویان
    0.38
     yat
    0.37
     Chatterjee
    0.36
     Pure
    0.36
    ())){
    0.35
     چاہ
    0.34
     explicitly
    0.34
    anı
    0.34
    POSITIVE LOGITS
     real
    0.88
     실제
    0.86
    実際の
    0.84
     реа
    0.83
     live
    0.79
    實際
    0.76
     actual
    0.75
     वास्तविक
    0.74
     practical
    0.73
    实际
    0.73
    Act Density 0.081%

    No Known Activations