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

    Neuronpedia

    INDEX
    Explanations

    public and open

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    后端
    0.38
     mammalian
    0.36
     උප
    0.36
    CategoryImage
    0.36
    ు
    0.36
    仙
    0.36
     backend
    0.35
    拏
    0.35
     edição
    0.35
    بع
    0.34
    POSITIVE LOGITS
    公开
    2.16
     openly
    2.11
     공개
    2.09
     publicly
    2.08
    公開
    2.03
     öffentlich
    1.66
     প্রকাশ্যে
    1.64
     public
    1.62
     публи
    1.58
     offent
    1.53
    Act Density 0.024%

    No Known Activations