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

    Neuronpedia

    INDEX
    Explanations

    thank you for your time

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    If
    0.70
    should
    0.64
     Если
    0.60
     ถ้า
    0.59
    ítja
    0.59
     अगर
    0.59
    ถ้า
    0.58
     केंद्रित
    0.58
    Якщо
    0.56
    Nếu
    0.55
    POSITIVE LOGITS
    வரின்
    0.52
    ありがとうございます
    0.50
    💐
    0.49
     🙏
    0.48
     comforting
    0.48
     eLearning
    0.48
    마
    0.48
     Pseudomonas
    0.48
     confidence
    0.47
    ョン
    0.46
    Act Density 0.146%

    No Known Activations