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

    Neuronpedia

    INDEX
    Explanations

    defining an expert role

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    IST
    0.48
    ্বস্ত
    0.46
     উর্
    0.46
    వన్
    0.45
    輋
    0.44
    एचओ
    0.42
    槭
    0.42
    ാർ
    0.41
     ईस्ट
    0.41
    ISTIC
    0.40
    POSITIVE LOGITS
     expert
    0.71
     экспер
    0.69
     experts
    0.67
     expertise
    0.64
     opinion
    0.63
     opin
    0.63
     Expert
    0.61
     Expertise
    0.61
     Experts
    0.61
     opinions
    0.60
    Act Density 0.007%

    No Known Activations