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

    Neuronpedia

    INDEX
    Explanations

    configuration files

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     gory
    0.71
     willful
    0.71
     sembl
    0.69
    ʀ
    0.68
    ᴀ
    0.64
     globular
    0.64
     bade
    0.63
     запла
    0.63
     Karp
    0.62
    加入了
    0.62
    POSITIVE LOGITS
    knings
    0.72
     निर्धारक
    0.71
     الخمسه
    0.70
    раста
    0.69
    érés
    0.68
    Quelle
    0.68
     خونه
    0.67
    untlet
    0.67
     Fractions
    0.66
    三菱
    0.66
    Act Density 0.146%

    No Known Activations