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

    Neuronpedia

    INDEX
    Explanations

    ending and resuming

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Restaurants
    0.88
     marriages
    0.87
     installer
    0.86
    agiarism
    0.84
    开设
    0.84
    拡散方程式
    0.84
     letteratura
    0.83
    restaurants
    0.83
    信用卡
    0.83
     Internship
    0.82
    POSITIVE LOGITS
     unless
    0.94
     partying
    0.86
    —
    0.84
    —“
    0.80
     awhile
    0.80
     वरना
    0.80
     doing
    0.78
     regardless
    0.77
    ;
    0.75
    ?
    0.75
    Act Density 0.147%

    No Known Activations