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

    Neuronpedia

    INDEX
    Explanations

    experience or enjoyable

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ้
    0.35
     말을
    0.34
    命令
    0.32
     गरज
    0.32
    க்கத்தில்
    0.32
    omely
    0.31
    言
    0.31
    เรียก
    0.31
    ਿਕ
    0.30
     দেরী
    0.30
    POSITIVE LOGITS
     experience
    1.73
    体验
    1.59
     pengalaman
    1.59
     experiences
    1.57
     experiencia
    1.57
     experiência
    1.54
    体験
    1.51
     enjoyable
    1.50
    體驗
    1.46
     अनुभव
    1.45
    Act Density 0.020%

    No Known Activations