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

    Neuronpedia

    INDEX
    Explanations

    outcomes and conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    4
    0.21
    粒
    0.19
    Você
    0.18
    німа
    0.18
    分为
    0.17
    ４
    0.17
     你
    0.17
    Downloads
    0.17
     teníamos
    0.16
    快捷
    0.16
    POSITIVE LOGITS
     thereby
    0.29
    从而
    0.25
     despite
    0.25
     Thereby
    0.23
     ainsi
    0.22
    だけでなく
    0.21
     সত্ত্বেও
    0.21
     serta
    0.20
     whereas
    0.20
     meskipun
    0.20
    Act Density 1.058%

    No Known Activations