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

    Neuronpedia

    INDEX
    Explanations

    Seriously you okay

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    まだ
    0.40
    DVD
    0.39
     продолжает
    0.39
     특
    0.39
    论坛
    0.39
    owers
    0.38
    mine
    0.38
     Illust
    0.38
     discussed
    0.38
    Did
    0.38
    POSITIVE LOGITS
     advice
    0.68
     advising
    0.57
     consigli
    0.54
    advice
    0.52
     Advice
    0.50
     aconsel
    0.49
     advise
    0.48
     conseils
    0.48
     conseille
    0.47
    Advice
    0.47
    Act Density 0.011%

    No Known Activations