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

    Neuronpedia

    INDEX
    Explanations

    overwhelmed by strong emotion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     extrêmement
    0.78
    非常に
    0.78
     अत्यंत
    0.74
     whatever
    0.70
    何か
    0.70
     extremadamente
    0.69
    极其
    0.68
     मिळ
    0.68
     qualcosa
    0.66
     extremamente
    0.66
    POSITIVE LOGITS
     amazed
    0.88
     speechless
    0.88
     shocked
    0.82
     surprised
    0.82
     stunned
    0.78
    November
    0.78
     shock
    0.78
     amazement
    0.77
     amaze
    0.75
     understatement
    0.74
    Act Density 0.115%

    No Known Activations