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

    Neuronpedia

    INDEX
    Explanations

    giving speeches

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     karma
    0.47
     বিশেষজ্ঞ
    0.46
     inline
    0.43
    லா
    0.42
     unprofessional
    0.42
     emojis
    0.42
     lazy
    0.42
     emoji
    0.41
     customer
    0.41
    द्द
    0.40
    POSITIVE LOGITS
     speeches
    1.95
     भाषण
    1.76
     speech
    1.52
    演讲
    1.52
     ভাষণ
    1.41
     संबोधन
    1.37
     Speech
    1.31
     বক্তৃতা
    1.31
    speech
    1.30
     orator
    1.29
    Act Density 0.011%

    No Known Activations