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

    Neuronpedia

    INDEX
    Explanations

    foreign languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     mocking
    0.51
    碜
    0.47
     harassing
    0.47
     học
    0.46
     headband
    0.46
     haf
    0.46
     त्यात
    0.46
     harass
    0.45
     chaud
    0.45
     mussten
    0.44
    POSITIVE LOGITS
    для
    0.49
     கிட்டத்தட்ட
    0.49
    Sites
    0.48
    अब
    0.47
    のための
    0.46
    現在
    0.46
    elés
    0.46
     現
    0.46
    Elon
    0.45
    OL
    0.45
    Act Density 0.028%

    No Known Activations