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

    Neuronpedia

    INDEX
    Explanations

    personal experiences and aspirations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    restaurants
    0.50
     restaurants
    0.48
     barons
    0.44
     billionaires
    0.44
     indemnify
    0.44
     sell
    0.44
    史上
    0.44
     booze
    0.44
     barbit
    0.43
     hotels
    0.43
    POSITIVE LOGITS
    我很
    0.56
     LinkedIn
    0.54
     خلال
    0.52
     joining
    0.52
     Challenges
    0.52
     volunteering
    0.51
     Passion
    0.50
    LinkedIn
    0.50
    振り返
    0.50
    Reflection
    0.49
    Act Density 0.053%

    No Known Activations