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

    Neuronpedia

    INDEX
    Explanations

    typename

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     size
    0.31
     mantuvo
    0.31
     yielding
    0.29
     resulting
    0.29
    ोर्ट
    0.29
     இதனால்
    0.29
     relatively
    0.29
     Ото
    0.29
     tangential
    0.28
    भे
    0.28
    POSITIVE LOGITS
     ذہنی
    0.36
     hm
    0.31
     osp
    0.30
     ماهی
    0.30
    ánsito
    0.29
    Ꭲ
    0.29
    မှာ
    0.29
    欱
    0.29
    Zinc
    0.29
     thụ
    0.28
    Act Density 0.001%

    No Known Activations