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

    Neuronpedia

    INDEX
    Explanations

    package management

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    pura
    0.39
     Waist
    0.38
    包括
    0.38
     Shrimp
    0.38
     CMP
    0.38
    痔
    0.38
     shrank
    0.37
     एक्सपे
    0.37
     এক্সচে
    0.37
     включа
    0.36
    POSITIVE LOGITS
     restoring
    0.43
     lock
    0.43
     restore
    0.41
     longing
    0.39
    ől
    0.39
     विश्वसनीय
    0.39
    坟
    0.39
    ̀n
    0.39
     managers
    0.38
    AT
    0.38
    Act Density 0.003%

    No Known Activations