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

    Neuronpedia

    INDEX
    Explanations

    enjoy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Excited
    0.41
     Choices
    0.40
     чыныгы
    0.38
     אם
    0.38
     அவர்களிடம்
    0.37
    Choices
    0.37
     Understand
    0.37
    Flood
    0.37
    crets
    0.37
    WORK
    0.37
    POSITIVE LOGITS
     amenities
    0.50
     enjoy
    0.49
     paradox
    0.49
    乐趣
    0.47
     responsibly
    0.46
     watching
    0.46
     life
    0.45
     spending
    0.45
    ably
    0.44
    the
    0.43
    Act Density 0.005%

    No Known Activations