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

    Neuronpedia

    INDEX
    Explanations

    supporting both or multiple

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    爾
    0.40
     ಅಥವಾ
    0.39
     Или
    0.38
    ربي
    0.38
     kanske
    0.37
    ğinin
    0.36
     allere
    0.36
     stargazerCount
    0.36
     tertentu
    0.36
    )\|_{
    0.36
    POSITIVE LOGITS
     problemlos
    0.66
     zowel
    0.66
     easily
    0.60
     både
    0.60
    多种
    0.57
     sowohl
    0.55
     facilement
    0.53
     both
    0.51
     facilmente
    0.51
     zarówno
    0.49
    Act Density 0.219%

    No Known Activations