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

    Neuronpedia

    INDEX
    Explanations

    content categories and descriptors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     microstructure
    0.40
     चतुर्थ
    0.39
     consect
    0.39
     jeux
    0.39
     več
    0.38
     negocios
    0.37
     යුතුය
    0.37
     weekends
    0.37
     pratis
    0.37
     Médico
    0.36
    POSITIVE LOGITS
     core
    0.46
    核心
    0.46
     Descriptor
    0.46
     Element
    0.43
    ᅯ
    0.41
     Elements
    0.41
     області
    0.41
     Core
    0.41
    DomainMask
    0.41
    Elements
    0.41
    Act Density 0.000%

    No Known Activations